Tootfinder

This is the main square in Piran, Slovenia, early morning today. Only 10 minutes away, the 22nd Extended Semantic Web Conference ESWC 2025 will take place, starting on Sunday, June 1st, 2025. I'm looking forward to meeting dear colleagues as well as old and new friends, listening to exciting keynotes, great presentations, and many more activities.

Bookmarked: Talking About Muslims in Middle French: The Potential of Word-to-Vector Models for Studying Semantic Relationships in Medieval Languages – DH Lab #Digital_Humanities

Talking About Muslims in Middle French: The Potential of Word-to-Vector Models for Studying Semantic Relationships in Medieval Languages
by Kimberly Lifton Medieval vernaculars are notoriously tricky for digital humanists to work with because they lack standardized spelling. Especially when using out-of-the-box libraries and software, most Natural Language Processing (NLP) techniques simply do not work well for medieval languages. However, word-to-vector models have the capacity to handle noise like spelling variants when trained on … „Talking About Muslims in Middle French: The Potential of Word-to-Vector Models for Studyin…

Bridging the Gap Between Semantic and User Preference Spaces for Multi-modal Music Representation Learning
Xiaofeng Pan, Jing Chen, Haitong Zhang, Menglin Xing, Jiayi Wei, Xuefeng Mu, Zhongqian Xie
https://arxiv.org/abs/2505.23298

Bridging the Gap Between Semantic and User Preference Spaces for Multi-modal Music Representation Learning
Recent works of music representation learning mainly focus on learning acoustic music representations with unlabeled audios or further attempt to acquire multi-modal music representations with scarce annotated audio-text pairs. They either ignore the language semantics or rely on labeled audio datasets that are difficult and expensive to create. Moreover, merely modeling semantic space usually fails to achieve satisfactory performance on music recommendation tasks since the user preference spac…

This https://arxiv.org/abs/2502.18200 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Zero-Shot Semantic Communication with Multimodal Foundation Models
Most existing semantic communication (SemCom) systems use deep joint source-channel coding (DeepJSCC) to encode task-specific semantics in a goal-oriented manner. However, their reliance on predefined tasks and datasets significantly limits their flexibility and generalizability in practical deployments. Multi-modal foundation models provide a promising solution by generating universal semantic tokens. Inspired by this, we introduce SemCLIP, a zero-shot SemCom framework leveraging the contrasti…

Context-Aware Semantic Communication for the Wireless Networks
Guangyuan Liu, Yinqiu Liu, Jiacheng Wang, Hongyang Du, Dusit Niyato, Jiawen Kang, Zehui Xiong, Abbas Jamalipour
https://arxiv.org/abs/2505.23249

Context-Aware Semantic Communication for the Wireless Networks
In next-generation wireless networks, supporting real-time applications such as augmented reality, autonomous driving, and immersive Metaverse services demands stringent constraints on bandwidth, latency, and reliability. Existing semantic communication (SemCom) approaches typically rely on static models, overlooking dynamic conditions and contextual cues vital for efficient transmission. To address these challenges, we propose CaSemCom, a context-aware SemCom framework that leverages a Large L…

This https://arxiv.org/abs/2401.13980 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIT_…

A Superposition Code-Based Semantic Communication Approach with Quantifiable and Controllable Security
This paper addresses the challenge of achieving security in semantic communication (SemCom) over a wiretap channel, where a legitimate receiver coexists with an eavesdropper experiencing a poorer channel condition. Despite previous efforts to secure SemCom against eavesdroppers, guarantee of approximately zero information leakage remains an open issue. In this work, we propose a secure SemCom approach based on superposition codes, aiming to provide quantifiable and controllable security for dig…

Unified Network-Based Representation of BIM Models for Embedding Semantic, Spatial, and Topological Data
Jin Han, Xin-Zheng Lu, Jia-Rui Lin
https://arxiv.org/abs/2505.22670

Unified Network-Based Representation of BIM Models for Embedding Semantic, Spatial, and Topological Data
Building Information Modeling (BIM) has revolutionized the construction industry by providing a comprehensive digital representation of building structures throughout their lifecycle. However, existing research lacks effective methods for capturing the complex spatial and topological relationships between components in BIM models, which are essential for understanding design patterns and enhancing decision-making. This study proposes a unified network-based representation method that integrates…

This https://arxiv.org/abs/2505.06612 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSI_…

Burger: Robust Graph Denoising-augmentation Fusion and Multi-semantic Modeling in Social Recommendation
In the era of rapid development of social media, social recommendation systems as hybrid recommendation systems have been widely applied. Existing methods capture interest similarity between users to filter out interest-irrelevant relations in social networks that inevitably decrease recommendation accuracy, however, limited research has a focus on the mutual influence of semantic information between the social network and the user-item interaction network for further improving social recommend…

SciMantify -- A Hybrid Approach for the Evolving Semantification of Scientific Knowledge
Lena John, Kheir Eddine Farfar, S\"oren Auer, Oliver Karras
https://arxiv.org/abs/2506.21819

SciMantify -- A Hybrid Approach for the Evolving Semantification of Scientific Knowledge
Scientific publications, primarily digitized as PDFs, remain static and unstructured, limiting the accessibility and reusability of the contained knowledge. At best, scientific knowledge from publications is provided in tabular formats, which lack semantic context. A more flexible, structured, and semantic representation is needed to make scientific knowledge understandable and processable by both humans and machines. We propose an evolution model of knowledge representation, inspired by the 5-…

Diffusion-based Task-oriented Semantic Communications with Model Inversion Attack
Xuesong Wang, Mo Li, Xingyan Shi, Zhaoqian Liu, Shenghao Yang
https://arxiv.org/abs/2506.19886

Diffusion-based Task-oriented Semantic Communications with Model Inversion Attack
Semantic communication has emerged as a promising neural network-based system design for 6G networks. Task-oriented semantic communication is a novel paradigm whose core goal is to efficiently complete specific tasks by transmitting semantic information, optimizing communication efficiency and task performance. The key challenge lies in preserving privacy while maintaining task accuracy, as this scenario is susceptible to model inversion attacks. In such attacks, adversaries can restore or even…

Wav2Sem: Plug-and-Play Audio Semantic Decoupling for 3D Speech-Driven Facial Animation
Hao Li, Ju Dai, Xin Zhao, Feng Zhou, Junjun Pan, Lei Li
https://arxiv.org/abs/2505.23290

Wav2Sem: Plug-and-Play Audio Semantic Decoupling for 3D Speech-Driven Facial Animation
In 3D speech-driven facial animation generation, existing methods commonly employ pre-trained self-supervised audio models as encoders. However, due to the prevalence of phonetically similar syllables with distinct lip shapes in language, these near-homophone syllables tend to exhibit significant coupling in self-supervised audio feature spaces, leading to the averaging effect in subsequent lip motion generation. To address this issue, this paper proposes a plug-and-play semantic decorrelation …

Bridging Compositional and Distributional Semantics: A Survey on Latent Semantic Geometry via AutoEncoder
Yingji Zhang, Danilo S. Carvalho, Andr\'e Freitas
https://arxiv.org/abs/2506.20083

Bridging Compositional and Distributional Semantics: A Survey on Latent Semantic Geometry via AutoEncoder
Integrating compositional and symbolic properties into current distributional semantic spaces can enhance the interpretability, controllability, compositionality, and generalisation capabilities of Transformer-based auto-regressive language models (LMs). In this survey, we offer a novel perspective on latent space geometry through the lens of compositional semantics, a direction we refer to as \textit{semantic representation learning}. This direction enables a bridge between symbolic and distri…

Modern applications require search capabilities that go beyond basic text matching. They must be fast, accurate, personalised and context-aware. At this year's Berlin Buzzwords, Saurabh Singh will demonstrate how OpenSearch’s latest AI/ML enhancements and engine improvements enable organisations to build intelligent, scalable search experiences that meet these evolving needs.
Learn more:

From Search to Insight: Leveraging OpenSearch for Scalable, AI-Driven Search Experiences
Observability, log analytics, GenAI systems, and RAG pipelines must query massive volumes of semantic embeddings to retrieve relevant content instantly. Today’s search systems often fall short in handling high-dimensional vector data and similarity search. OpenSearch 3.0 brings significant architectural improvements to address these challenges. Integrating Apache Lucene 10 and JVM 21, the platform delivers 20% faster queries than its 2.x predecessor and 10× the throughput of 1.x versions. Ne…

Wireless Agentic AI with Retrieval-Augmented Multimodal Semantic Perception
Guangyuan Liu, Yinqiu Liu, Ruichen Zhang, Hongyang Du, Dusit Niyato, Zehui Xiong, Sumei Sun, Abbas Jamalipour
https://arxiv.org/abs/2505.23275

Wireless Agentic AI with Retrieval-Augmented Multimodal Semantic Perception
The rapid development of multimodal AI and Large Language Models (LLMs) has greatly enhanced real-time interaction, decision-making, and collaborative tasks. However, in wireless multi-agent scenarios, limited bandwidth poses significant challenges to exchanging semantically rich multimodal information efficiently. Traditional semantic communication methods, though effective, struggle with redundancy and loss of crucial details. To overcome these challenges, we propose a Retrieval-Augmented Mul…

SPARK: Graph-Based Online Semantic Integration System for Robot Task Planning
Mimo Shirasaka, Yuya Ikeda, Tatsuya Matsushima, Yutaka Matsuo, Yusuke Iwasawa
https://arxiv.org/abs/2506.20394

SPARK: Graph-Based Online Semantic Integration System for Robot Task Planning
The ability to update information acquired through various means online during task execution is crucial for a general-purpose service robot. This information includes geometric and semantic data. While SLAM handles geometric updates on 2D maps or 3D point clouds, online updates of semantic information remain unexplored. We attribute the challenge to the online scene graph representation, for its utility and scalability. Building on previous works regarding offline scene graph representations, …

Building Lightweight Semantic Segmentation Models for Aerial Images Using Dual Relation Distillation
Minglong Li, Lianlei Shan, Weiqiang Wang, Ke Lv, Bin Luo, Si-Bao Chen
https://arxiv.org/abs/2506.20688

Building Lightweight Semantic Segmentation Models for Aerial Images Using Dual Relation Distillation
Recently, there have been significant improvements in the accuracy of CNN models for semantic segmentation. However, these models are often heavy and suffer from low inference speed, which limits their practical application. To address this issue, knowledge distillation has emerged as a promising approach to achieve a good trade-off between segmentation accuracy and efficiency. In this paper, we propose a novel dual relation distillation (DRD) technique that transfers both spatial and channel r…

On the Consistency of Peano Arithmetic in a Proof-theoretic Semantics for Classical Logic
Alexander V. Gheorghiu
https://arxiv.org/abs/2506.22326 https://

On the Consistency of Peano Arithmetic in a Proof-theoretic Semantics for Classical Logic
We give a proof of the consistency of Peano Arithmetic (PA) within a novel semantic framework for classical logic due to Sandqvist. The argument proceeds by constructing an object $\mathfrak{A}$ -- the arithmetic base -- which supports all axioms of PA and can be shown to not support $\bot$, relative to a well-foundedness assumption equivalent to $ε_0$-induction. This framework belongs to the paradigm of proof-theoretic semantics, that unlike model-theoretic approaches, offers a finitistically…

Augment or Not? A Comparative Study of Pure and Augmented Large Language Model Recommenders
Wei-Hsiang Huang, Chen-Wei Ke, Wei-Ning Chiu, Yu-Xuan Su, Chun-Chun Yang, Chieh-Yuan Cheng, Yun-Nung Chen, Pu-Jen Cheng
https://arxiv.org/abs/2505.23053

Augment or Not? A Comparative Study of Pure and Augmented Large Language Model Recommenders
Large language models (LLMs) have introduced new paradigms for recommender systems by enabling richer semantic understanding and incorporating implicit world knowledge. In this study, we propose a systematic taxonomy that classifies existing approaches into two categories: (1) Pure LLM Recommenders, which rely solely on LLMs, and (2) Augmented LLM Recommenders, which integrate additional non-LLM techniques to enhance performance. This taxonomy provides a novel lens through which to examine the …

This https://arxiv.org/abs/2503.09663 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csOS_…

BYOS: Knowledge-driven Large Language Models Bring Your Own Operating System More Excellent
Operating System (OS) kernel tuning involves systematically adjusting kernel configurations to optimize system performance. Despite recent advancements in large language models (LLMs), kernel tuning remains a critical challenge due to: (1) the semantic gap between abstract tuning objective and concrete config options, (2) insufficient environmental interaction induces LLM hallucinations, and (3) the rapid evolution of kernel versions. To address these challenges, we propose BYOS, a LLM-powered …

Semantic-aware Digital Twin for AI-based CSI Acquisition
Jiajia Guo, Yiming Cui, Shi Jin
https://arxiv.org/abs/2506.21126 https://arx…

Semantic-aware Digital Twin for AI-based CSI Acquisition
Artificial intelligence (AI) substantially enhances channel state information (CSI) acquisition performance but is limited by its reliance on single-modality information and deployment challenges, particularly in dataset collection. This paper investigates the use of semantic-aware digital twin (DT) to enhance AI-based CSI acquisition. We first briefly introduce the motivation and recent advancements in AI-driven CSI acquisition and semantic-aware DT employment for air interfaces. Then, we thor…

Intrinsic vs. Extrinsic Evaluation of Czech Sentence Embeddings: Semantic Relevance Doesn't Help with MT Evaluation
Petra Baran\v{c}\'ikov\'a, Ond\v{r}ej Bojar
https://arxiv.org/abs/2506.20203

Intrinsic vs. Extrinsic Evaluation of Czech Sentence Embeddings: Semantic Relevance Doesn't Help with MT Evaluation
In this paper, we compare Czech-specific and multilingual sentence embedding models through intrinsic and extrinsic evaluation paradigms. For intrinsic evaluation, we employ Costra, a complex sentence transformation dataset, and several Semantic Textual Similarity (STS) benchmarks to assess the ability of the embeddings to capture linguistic phenomena such as semantic similarity, temporal aspects, and stylistic variations. In the extrinsic evaluation, we fine-tune each embedding model using COM…

TrajSceneLLM: A Multimodal Perspective on Semantic GPS Trajectory Analysis
Chunhou Ji, Qiumeng Li
https://arxiv.org/abs/2506.16401 https://

TrajSceneLLM: A Multimodal Perspective on Semantic GPS Trajectory Analysis
GPS trajectory data reveals valuable patterns of human mobility and urban dynamics, supporting a variety of spatial applications. However, traditional methods often struggle to extract deep semantic representations and incorporate contextual map information. We propose TrajSceneLLM, a multimodal perspective for enhancing semantic understanding of GPS trajectories. The framework integrates visualized map images (encoding spatial context) and textual descriptions generated through LLM reasoning (…

Dive into semantic reranking at Berlin Buzzwords 2025! Athanasios Papaoikonomou will explore how different models and reranking depths impact search performance, revealing important patterns and the real-world efficiency vs. effectiveness trade-off.
Learn more: https://

Exploring reranking depth in modern search pipelines
The use of semantic reranking on top of a ‘cheaper’ retrieval step becomes more and more common in modern search applications. It offers a different cost quality profile to semantic retrieval trading indexing time compute for retrieval time compute. The depth represents the number of documents that we select to retrieve and feed into the reranking model in order to optimise their ordering. Intuitively, there is a “natural” trade-off between the uplift we can achieve by operating on an i…

Performance improvement of spatial semantic segmentation with enriched audio features and agent-based error correction for DCASE 2025 Challenge Task 4
Jongyeon Park, Joonhee Lee, Do-Hyeon Lim, Hong Kook Kim, Hyeongcheol Geum, Jeong Eun Lim
https://arxiv.org/abs/2506.21174

Performance improvement of spatial semantic segmentation with enriched audio features and agent-based error correction for DCASE 2025 Challenge Task 4
This technical report presents submission systems for Task 4 of the DCASE 2025 Challenge. This model incorporates additional audio features (spectral roll-off and chroma features) into the embedding feature extracted from the mel-spectral feature to im-prove the classification capabilities of an audio-tagging model in the spatial semantic segmentation of sound scenes (S5) system. This approach is motivated by the fact that mixed audio often contains subtle cues that are difficult to capture wit…

Semantic Scaffolding: Augmenting Textual Structures with Domain-Specific Groupings for Accessible Data Exploration
Jonathan Zong, Isabella Pedraza Pineros, Mengzhu Katie Chen, Daniel Hajas, Arvind Satyanarayan
https://arxiv.org/abs/2506.15883

Semantic Scaffolding: Augmenting Textual Structures with Domain-Specific Groupings for Accessible Data Exploration
Drawing connections between interesting groupings of data and their real-world meaning is an important, yet difficult, part of encountering a new dataset. A lay reader might see an interesting visual pattern in a chart but lack the domain expertise to explain its meaning. Or, a reader might be familiar with a real-world concept but struggle to express it in terms of a dataset's fields. In response, we developed semantic scaffolding, a technique for using domain-specific information from large l…

The time course of visuo-semantic representations in the human brain is captured by combining vision and language models
Boyan Rong, Alessandro Thomas Gifford, Emrah D\"uzel, Radoslaw Martin Cichy
https://arxiv.org/abs/2506.19497

The time course of visuo-semantic representations in the human brain is captured by combining vision and language models
The human visual system provides us with a rich and meaningful percept of the world, transforming retinal signals into visuo-semantic representations. For a model of these representations, here we leveraged a combination of two currently dominating approaches: vision deep neural networks (DNNs) and large language models (LLMs). Using large-scale human electroencephalography (EEG) data recorded during object image viewing, we built encoding models to predict EEG responses using representations f…

Deep Retrieval at CheckThat! 2025: Identifying Scientific Papers from Implicit Social Media Mentions via Hybrid Retrieval and Re-Ranking
Pascal J. Sager, Ashwini Kamaraj, Benjamin F. Grewe, Thilo Stadelmann
https://arxiv.org/abs/2505.23250

Deep Retrieval at CheckThat! 2025: Identifying Scientific Papers from Implicit Social Media Mentions via Hybrid Retrieval and Re-Ranking
We present the methodology and results of the Deep Retrieval team for subtask 4b of the CLEF CheckThat! 2025 competition, which focuses on retrieving relevant scientific literature for given social media posts. To address this task, we propose a hybrid retrieval pipeline that combines lexical precision, semantic generalization, and deep contextual re-ranking, enabling robust retrieval that bridges the informal-to-formal language gap. Specifically, we combine BM25-based keyword matching with a F…

Re-Evaluating Code LLM Benchmarks Under Semantic Mutation
Zhiyuan Pan, Xing Hu, Xin Xia, Xiaohu Yang
https://arxiv.org/abs/2506.17369 https://

Re-Evaluating Code LLM Benchmarks Under Semantic Mutation
In the era of large language models (LLMs), code benchmarks have become an important research area in software engineering and are widely used by practitioners. These benchmarks evaluate the performance of LLMs on specific code-related tasks, such as code understanding and generation. A critical step in constructing code benchmarks is the design of prompts. However, as existing code benchmarks typically rely on a single prompt template per task, they are prone to the issue of prompt sensitivity…

Mitigating Hallucination of Large Vision-Language Models via Dynamic Logits Calibration
Jiahe Chen, Jiaying He, Qian Shao, Qiyuan Chen, Jiahe Ying, Hongxia Xu, Jintai Chen, Jianwei Zheng, Jian Wu
https://arxiv.org/abs/2506.21509

Mitigating Hallucination of Large Vision-Language Models via Dynamic Logits Calibration
Large Vision-Language Models (LVLMs) have demonstrated significant advancements in multimodal understanding, yet they are frequently hampered by hallucination-the generation of text that contradicts visual input. Existing training-free decoding strategies exhibit critical limitations, including the use of static constraints that do not adapt to semantic drift during generation, inefficiency stemming from the need for multiple forward passes, and degradation of detail due to overly rigid interve…

(YouTube) A world's first for the blind! The vOICe web app and Google Gemini Live demo: simultaneous "raw" vision from visual-to-auditory sensory substitution and AI-based verbal descriptions for "semantic" vision https://www.youtube.com/watch?v=506BvU8oMmM

PBFT-Backed Semantic Voting for Multi-Agent Memory Pruning
Duong Bach
https://arxiv.org/abs/2506.17338 https://arxiv.org/pdf/2506.173…

PBFT-Backed Semantic Voting for Multi-Agent Memory Pruning
The proliferation of multi-agent systems (MAS) in complex, dynamic environments necessitates robust and efficient mechanisms for managing shared knowledge. A critical challenge is ensuring that distributed memories remain synchronized, relevant, and free from the accumulation of outdated or inconsequential data - a process analogous to biological forgetting. This paper introduces the Co-Forgetting Protocol, a novel, comprehensive framework designed to address this challenge by enabling synchron…

Knowledge-Driven Imitation Learning: Enabling Generalization Across Diverse Conditions
Zhuochen Miao, Jun Lv, Hongjie Fang, Yang Jin, Cewu Lu
https://arxiv.org/abs/2506.21057

Knowledge-Driven Imitation Learning: Enabling Generalization Across Diverse Conditions
Imitation learning has emerged as a powerful paradigm in robot manipulation, yet its generalization capability remains constrained by object-specific dependencies in limited expert demonstrations. To address this challenge, we propose knowledge-driven imitation learning, a framework that leverages external structural semantic knowledge to abstract object representations within the same category. We introduce a novel semantic keypoint graph as a knowledge template and develop a coarse-to-fine te…

U-R-VEDA: Integrating UNET, Residual Links, Edge and Dual Attention, and Vision Transformer for Accurate Semantic Segmentation of CMRs
Racheal Mukisa, Arvind K. Bansal
https://arxiv.org/abs/2506.20689

U-R-VEDA: Integrating UNET, Residual Links, Edge and Dual Attention, and Vision Transformer for Accurate Semantic Segmentation of CMRs
Artificial intelligence, including deep learning models, will play a transformative role in automated medical image analysis for the diagnosis of cardiac disorders and their management. Automated accurate delineation of cardiac images is the first necessary initial step for the quantification and automated diagnosis of cardiac disorders. In this paper, we propose a deep learning based enhanced UNet model, U-R-Veda, which integrates convolution transformations, vision transformer, residual links…

LLMs the Model Context Protocol (MCP) are the Yang to the Semantic Web Project's Yin.
We now have a solution to the final hurdle—visualization.
Years of Linked Data work now come alive. I explain this, with demonstrations, in a new newsletter post.
www.linkedin.com/pulse/semant...
#MCP

Into the Unknown: Applying Inductive Spatial-Semantic Location Embeddings for Predicting Individuals' Mobility Beyond Visited Places
Xinglei Wang, Tao Cheng, Stephen Law, Zichao Zeng, Ilya Ilyankou, Junyuan Liu, Lu Yin, Weiming Huang, Natchapon Jongwiriyanurak
https://arxiv.org/abs/2506.14070…

Into the Unknown: Applying Inductive Spatial-Semantic Location Embeddings for Predicting Individuals' Mobility Beyond Visited Places
Predicting individuals' next locations is a core task in human mobility modelling, with wide-ranging implications for urban planning, transportation, public policy and personalised mobility services. Traditional approaches largely depend on location embeddings learned from historical mobility patterns, limiting their ability to encode explicit spatial information, integrate rich urban semantic context, and accommodate previously unseen locations. To address these challenges, we explore the appl…

RL-Driven Semantic Compression Model Selection and Resource Allocation in Semantic Communication Systems
Xinyi Lin, Peizheng Li, Adnan Aijaz
https://arxiv.org/abs/2506.18660

RL-Driven Semantic Compression Model Selection and Resource Allocation in Semantic Communication Systems
Semantic communication (SemCom) is an emerging paradigm that leverages semantic-level understanding to improve communication efficiency, particularly in resource-constrained scenarios. However, existing SemCom systems often overlook diverse computational and communication capabilities and requirements among different users. Motivated by the need to adaptively balance semantic accuracy, latency, and energy consumption, this paper presents a reinforcement learning (RL)-driven framework for semant…

Recursive Semantic Anchoring in ISO 639:2023: A Structural Extension to ISO/TC 37 Frameworks
Bugra Kilictas, Faruk Alpay
https://arxiv.org/abs/2506.06870 h…

Recursive Semantic Anchoring in ISO 639:2023: A Structural Extension to ISO/TC 37 Frameworks
ISO 639:2023 unifies the ISO language-code family and introduces contextual metadata, but it lacks a machine-native mechanism for handling dialectal drift and creole mixtures. We propose a formalisation of recursive semantic anchoring, attaching to every language entity $χ$ a family of fixed-point operators $ϕ_{n,m}$ that model bounded semantic drift via the relation $ϕ_{n,m}(χ) = χ\oplus Δ(χ)$, where $Δ(χ)$ is a drift vector in a latent semantic manifold. The base anchor $ϕ_{0,0}$ re…

TFW you build a site with @… and web platform standards (== semantic HTML, modern CSS, a little bit of JavaScript, and a dash of ARIA) and you look at Lighthouse for the first time …
Looks like industry best practices actually work. (Sorry for using my platform to ruin anyone’s day. 🥰) 🍋

Semantics-Aware Human Motion Generation from Audio Instructions
Zi-An Wang, Shihao Zou, Shiyao Yu, Mingyuan Zhang, Chao Dong
https://arxiv.org/abs/2505.23465

Semantics-Aware Human Motion Generation from Audio Instructions
Recent advances in interactive technologies have highlighted the prominence of audio signals for semantic encoding. This paper explores a new task, where audio signals are used as conditioning inputs to generate motions that align with the semantics of the audio. Unlike text-based interactions, audio provides a more natural and intuitive communication method. However, existing methods typically focus on matching motions with music or speech rhythms, which often results in a weak connection betw…

Measuring Semantic Information Production in Generative Diffusion Models
Florian Handke, F\'elix Koulischer, Gabriel Raya, Luca Ambrogioni
https://arxiv.org/abs/2506.10433

Measuring Semantic Information Production in Generative Diffusion Models
It is well known that semantic and structural features of the generated images emerge at different times during the reverse dynamics of diffusion, a phenomenon that has been connected to physical phase transitions in magnets and other materials. In this paper, we introduce a general information-theoretic approach to measure when these class-semantic "decisions" are made during the generative process. By using an online formula for the optimal Bayesian classifier, we estimate the conditional ent…

Semantic-enhanced Modality-asymmetric Retrieval for Online E-commerce Search
Zhigong Zhou, Ning Ding, Xiaochuan Fan, Yue Shang, Yiming Qiu, Jingwei Zhuo, Zhiwei Ge, Songlin Wang, Lin Liu, Sulong Xu, Han Zhang
https://arxiv.org/abs/2506.20330

Semantic-enhanced Modality-asymmetric Retrieval for Online E-commerce Search
Semantic retrieval, which retrieves semantically matched items given a textual query, has been an essential component to enhance system effectiveness in e-commerce search. In this paper, we study the multimodal retrieval problem, where the visual information (e.g, image) of item is leveraged as supplementary of textual information to enrich item representation and further improve retrieval performance. Though learning from cross-modality data has been studied extensively in tasks such as visual…

StoryGem: Voronoi treemap Approach for Semantics-Preserving Text Visualization
Naoya Oda, Yosuke Onoue
https://arxiv.org/abs/2506.18793 https://

StoryGem: Voronoi treemap Approach for Semantics-Preserving Text Visualization
Word cloud use is a popular text visualization technique that scales font sizes based on word frequencies within a defined spatial layout. However, traditional word clouds disregard semantic relationships between words, arranging them without considering their meanings. Semantic word clouds improved on this by positioning related words in proximity; however, still struggled with efficient space use and representing frequencies through font size variations, which can be misleading because of wor…

PrivacyXray: Detecting Privacy Breaches in LLMs through Semantic Consistency and Probability Certainty
Jinwen He, Yiyang Lu, Zijin Lin, Kai Chen, Yue Zhao
https://arxiv.org/abs/2506.19563

PrivacyXray: Detecting Privacy Breaches in LLMs through Semantic Consistency and Probability Certainty
Large Language Models (LLMs) are widely used in sensitive domains, including healthcare, finance, and legal services, raising concerns about potential private information leaks during inference. Privacy extraction attacks, such as jailbreaking, expose vulnerabilities in LLMs by crafting inputs that force the models to output sensitive information. However, these attacks cannot verify whether the extracted private information is accurate, as no public datasets exist for cross-validation, leaving…

DiffSoundStream: Efficient Speech Tokenization via Diffusion Decoding
Yang Yang, Yunpeng Li, George Sung, Shao-Fu Shih, Craig Dooley, Alessio Centazzo, Ramanan Rajeswaran
https://arxiv.org/abs/2506.22362

DiffSoundStream: Efficient Speech Tokenization via Diffusion Decoding
Token-based language modeling is a prominent approach for speech generation, where tokens are obtained by quantizing features from self-supervised learning (SSL) models and extracting codes from neural speech codecs, generally referred to as semantic tokens and acoustic tokens. These tokens are often modeled autoregressively, with the inference speed being constrained by the token rate. In this work, we propose DiffSoundStream, a solution that improves the efficiency of speech tokenization in n…

Announcing sff: A fast, on-the-fly SemanticFileFinder written in Rust! 🦀
It scans a directory (like your notes or a repo), finds the most semantically relevant text chunks for your query, and lets you open the file in a text editor of your choice.
No vector DBs, no GPU needed. Indexes ~2500 files with 10k chunks in 250ms on a CPU.
Perfect for searching Obsidian vaults, codebases, and more.
𝚌𝚊𝚛𝚐𝚘 𝚒𝚗𝚜𝚝𝚊𝚕𝚕 𝚜𝚏𝚏
𝚜𝚏𝚏 "𝚠𝚘𝚛𝚔𝚒𝚗𝚐 𝚠𝚒𝚝𝚑 𝚐𝚒𝚝"

GitHub - do-me/sff: CLI for semantic search on your computer. Searches text files and identifies the most relevant chunks to your query.
CLI for semantic search on your computer. Searches text files and identifies the most relevant chunks to your query. - GitHub - do-me/sff: CLI for semantic search on your computer. Searches text f...

SACL: Understanding and Combating Textual Bias in Code Retrieval with Semantic-Augmented Reranking and Localization
Dhruv Gupta, Gayathri Ganesh Lakshmy, Yiqing Xie
https://arxiv.org/abs/2506.20081

SACL: Understanding and Combating Textual Bias in Code Retrieval with Semantic-Augmented Reranking and Localization
Retrieval-Augmented Code Generation (RACG) is a critical technique for enhancing code generation by retrieving relevant information. In this work, we conduct an in-depth analysis of code retrieval by systematically masking specific features while preserving code functionality. Our discoveries include: (1) although trained on code, current retrievers heavily rely on surface-level textual features (e.g., docstrings, identifier names), and (2) they exhibit a strong bias towards well-documented cod…

Join Dennis Berger, Marco Petris, and Volker Carlguth to explore 'Intent-Based Clustering.' An approach to overcome some limitations of modern hybrid search systems. Discover how upfront LLM-supported in-depth query understanding can be applied in various steps, including retrieval, clustering, validation, and presentation. Learn about the process of moving from prototype to production for large-scale, high-volume e-commerce searches.

What you see is what you mean; intent based ecommerce search
In today's e-commerce landscape, hybrid search systems represent the market standard, yet they often struggle with highly inspirational queries, lack of precision in semantic recall, and presentation of diversity. Ambiguity in search terms can lead to disorganized results or overshadowed relevant products. This session will demonstrate how an upfront LLM-supported in depth query understanding can increase recall meaningfully without sacrificing precision. We show how LLM-driven query understand…

Low-Complexity Semantic Packet Aggregation for Token Communication via Lookahead Search
Seunghun Lee, Jihong Park, Jinho Choi, Hyuncheol Park
https://arxiv.org/abs/2506.19451

Low-Complexity Semantic Packet Aggregation for Token Communication via Lookahead Search
Tokens are fundamental processing units of generative AI (GenAI) and large language models (LLMs), and token communication (TC) is essential for enabling remote AI-generate content (AIGC) and wireless LLM applications. Unlike traditional bits, each of which is independently treated, the semantics of each token depends on its surrounding context tokens. This inter-token dependency makes TC vulnerable to outage channels, where the loss of a single token can significantly distort the original mess…

SAVANT: Vulnerability Detection in Application Dependencies through Semantic-Guided Reachability Analysis
Wang Lingxiang, Quanzhi Fu, Wenjia Song, Gelei Deng, Yi Liu, Dan Williams, Ying Zhang
https://arxiv.org/abs/2506.17798

SAVANT: Vulnerability Detection in Application Dependencies through Semantic-Guided Reachability Analysis
The integration of open-source third-party library dependencies in Java development introduces significant security risks when these libraries contain known vulnerabilities. Existing Software Composition Analysis (SCA) tools struggle to effectively detect vulnerable API usage from these libraries due to limitations in understanding API usage semantics and computational challenges in analyzing complex codebases, leading to inaccurate vulnerability alerts that burden development teams and delay c…

This https://arxiv.org/abs/2405.20032 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csNI_…

Promptus: Can Prompts Streaming Replace Video Streaming with Stable Diffusion
With the exponential growth of video traffic, traditional video streaming systems are approaching their limits in compression efficiency and communication capacity. To further reduce bitrate while maintaining quality, we propose Promptus, a disruptive semantic communication system that streaming prompts instead of video content, which represents real-world video frames with a series of "prompts" for delivery and employs Stable Diffusion to generate videos at the receiver. To ensure that the gen…

IPFormer: Visual 3D Panoptic Scene Completion with Context-Adaptive Instance Proposals
Markus Gross, Aya Fahmy, Danit Niwattananan, Dominik Muhle, Rui Song, Daniel Cremers, Henri Mee{\ss}
https://arxiv.org/abs/2506.20671

IPFormer: Visual 3D Panoptic Scene Completion with Context-Adaptive Instance Proposals
Semantic Scene Completion (SSC) has emerged as a pivotal approach for jointly learning scene geometry and semantics, enabling downstream applications such as navigation in mobile robotics. The recent generalization to Panoptic Scene Completion (PSC) advances the SSC domain by integrating instance-level information, thereby enhancing object-level sensitivity in scene understanding. While PSC was introduced using LiDAR modality, methods based on camera images remain largely unexplored. Moreover, …

A Survey of Multi-sensor Fusion Perception for Embodied AI: Background, Methods, Challenges and Prospects
Shulan Ruan, Rongwei Wang, Xuchen Shen, Huijie Liu, Baihui Xiao, Jun Shi, Kun Zhang, Zhenya Huang, Yu Liu, Enhong Chen, You He
https://arxiv.org/abs/2506.19769

A Survey of Multi-sensor Fusion Perception for Embodied AI: Background, Methods, Challenges and Prospects
Multi-sensor fusion perception (MSFP) is a key technology for embodied AI, which can serve a variety of downstream tasks (e.g., 3D object detection and semantic segmentation) and application scenarios (e.g., autonomous driving and swarm robotics). Recently, impressive achievements on AI-based MSFP methods have been reviewed in relevant surveys. However, we observe that the existing surveys have some limitations after a rigorous and detailed investigation. For one thing, most surveys are oriente…

Semantic Caching for Improving Web Affordability
Hafsa Akbar, Danish Athar, Muhammad Ayain Fida Rana, Chaudhary Hammad Javed, Zartash Afzal Uzmi, Ihsan Ayyub Qazi, Zafar Ayyub Qazi
https://arxiv.org/abs/2506.20420

Semantic Caching for Improving Web Affordability
The rapid growth of web content has led to increasingly large webpages, posing significant challenges for Internet affordability, especially in developing countries where data costs remain prohibitively high. We propose semantic caching using Large Language Models (LLMs) to improve web affordability by enabling reuse of semantically similar images within webpages. Analyzing 50 leading news and media websites, encompassing 4,264 images and over 40,000 image pairs, we demonstrate potential for si…

DHoTT: A Temporal Extension of Homotopy Type Theory for Semantic Drift
Iman Poernomo
https://arxiv.org/abs/2506.09671 https://arxiv.o…

DHoTT: A Temporal Extension of Homotopy Type Theory for Semantic Drift
We introduce Dynamic Homotopy Type Theory (DHoTT), a temporal extension of Homotopy Type Theory (HoTT) designed to reason formally about concepts whose meanings evolve continuously or rupture discontinuously over time. While traditional HoTT captures identity and equivalence within a fixed semantic landscape, DHoTT enriches this framework by explicitly indexing types with a temporal parameter, allowing types themselves to deform, rupture, and reassemble as contexts shift. Formally, we show th…

Domain Knowledge-Enhanced LLMs for Fraud and Concept Drift Detection
Ali \c{S}enol, Garima Agrawal, Huan Liu
https://arxiv.org/abs/2506.21443 https://arxiv.org/pdf/2506.21443 https://arxiv.org/html/2506.21443
arXiv:2506.21443v1 Announce Type: new
Abstract: Detecting deceptive conversations on dynamic platforms is increasingly difficult due to evolving language patterns and Concept Drift (CD)\-i.e., semantic or topical shifts that alter the context or intent of interactions over time. These shifts can obscure malicious intent or mimic normal dialogue, making accurate classification challenging. While Large Language Models (LLMs) show strong performance in natural language tasks, they often struggle with contextual ambiguity and hallucinations in risk\-sensitive scenarios. To address these challenges, we present a Domain Knowledge (DK)\-Enhanced LLM framework that integrates pretrained LLMs with structured, task\-specific insights to perform fraud and concept drift detection. The proposed architecture consists of three main components: (1) a DK\-LLM module to detect fake or deceptive conversations; (2) a drift detection unit (OCDD) to determine whether a semantic shift has occurred; and (3) a second DK\-LLM module to classify the drift as either benign or fraudulent. We first validate the value of domain knowledge using a fake review dataset and then apply our full framework to SEConvo, a multiturn dialogue dataset that includes various types of fraud and spam attacks. Results show that our system detects fake conversations with high accuracy and effectively classifies the nature of drift. Guided by structured prompts, the LLaMA\-based implementation achieves 98\% classification accuracy. Comparative studies against zero\-shot baselines demonstrate that incorporating domain knowledge and drift awareness significantly improves performance, interpretability, and robustness in high\-stakes NLP applications.
toXiv_bot_toot

medicX-KG: A Knowledge Graph for Pharmacists' Drug Information Needs
Lizzy Farrugia, Lilian M. Azzopardi, Jeremy Debattista, Charlie Abela
https://arxiv.org/abs/2506.17959

medicX-KG: A Knowledge Graph for Pharmacists' Drug Information Needs
The role of pharmacists is evolving from medicine dispensing to delivering comprehensive pharmaceutical services within multidisciplinary healthcare teams. Central to this shift is access to accurate, up-to-date medicinal product information supported by robust data integration. Leveraging artificial intelligence and semantic technologies, Knowledge Graphs (KGs) uncover hidden relationships and enable data-driven decision-making. This paper presents medicX-KG, a pharmacist-oriented knowledge gr…

Show, Tell and Summarize: Dense Video Captioning Using Visual Cue Aided Sentence Summarization
Zhiwang Zhang, Dong Xu, Wanli Ouyang, Chuanqi Tan
https://arxiv.org/abs/2506.20567

Show, Tell and Summarize: Dense Video Captioning Using Visual Cue Aided Sentence Summarization
In this work, we propose a division-and-summarization (DaS) framework for dense video captioning. After partitioning each untrimmed long video as multiple event proposals, where each event proposal consists of a set of short video segments, we extract visual feature (e.g., C3D feature) from each segment and use the existing image/video captioning approach to generate one sentence description for this segment. Considering that the generated sentences contain rich semantic descriptions about the …

DiscRec: Disentangled Semantic-Collaborative Modeling for Generative Recommendation
Chang Liu, Yimeng Bai, Xiaoyan Zhao, Yang Zhang, Fuli Feng, Wenge Rong
https://arxiv.org/abs/2506.15576

DiscRec: Disentangled Semantic-Collaborative Modeling for Generative Recommendation
Generative recommendation is emerging as a powerful paradigm that directly generates item predictions, moving beyond traditional matching-based approaches. However, current methods face two key challenges: token-item misalignment, where uniform token-level modeling ignores item-level granularity that is critical for collaborative signal learning, and semantic-collaborative signal entanglement, where collaborative and semantic signals exhibit distinct distributions yet are fused in a unified emb…

AutoGraph: A Knowledge-Graph Framework for Modeling Interface Interaction and Automating Procedure Execution in Digital Nuclear Control Rooms
Xingyu Xiao, Jiejuan Tong, Jun Sun, Zhe Sui, Jingang Liang, Hongru Zhao, Jun Zhao, Haitao Wang
https://arxiv.org/abs/2506.18727

AutoGraph: A Knowledge-Graph Framework for Modeling Interface Interaction and Automating Procedure Execution in Digital Nuclear Control Rooms
Digitalization in nuclear power plant (NPP) control rooms is reshaping how operators interact with procedures and interface elements. However, existing computer-based procedures (CBPs) often lack semantic integration with human-system interfaces (HSIs), limiting their capacity to support intelligent automation and increasing the risk of human error, particularly under dynamic or complex operating conditions. In this study, we present AutoGraph, a knowledge-graph-based framework designed to form…

Stacked Intelligent Metasurfaces for Multi-Modal Semantic Communications
Guojun Huang, Jiancheng An, Lu Gan, Dusit Niyato, M\'erouane Debbah, Tie Jun Cui
https://arxiv.org/abs/2506.12368

Stacked Intelligent Metasurfaces for Multi-Modal Semantic Communications
Semantic communication (SemCom) powered by generative artificial intelligence enables highly efficient and reliable information transmission. However, it still necessitates the transmission of substantial amounts of data when dealing with complex scene information. In contrast, the stacked intelligent metasurface (SIM), leveraging wave-domain computing, provides a cost-effective solution for directly imaging complex scenes. Building on this concept, we propose an innovative SIM-aided multi-moda…

SEMNAV: A Semantic Segmentation-Driven Approach to Visual Semantic Navigation
Rafael Flor-Rodr\'iguez, Carlos Guti\'errez-\'Alvarez, Francisco Javier Acevedo-Rodr\'iguez, Sergio Lafuente-Arroyo, Roberto J. L\'opez-Sastre
https://arxiv.org/abs/2506.01418

SEMNAV: A Semantic Segmentation-Driven Approach to Visual Semantic Navigation
Visual Semantic Navigation (VSN) is a fundamental problem in robotics, where an agent must navigate toward a target object in an unknown environment, mainly using visual information. Most state-of-the-art VSN models are trained in simulation environments, where rendered scenes of the real world are used, at best. These approaches typically rely on raw RGB data from the virtual scenes, which limits their ability to generalize to real-world environments due to domain adaptation issues. To tackle …

Client Selection Strategies for Federated Semantic Communications in Heterogeneous IoT Networks
Samer Lahoud, Kinda Khawam
https://arxiv.org/abs/2506.17063

Client Selection Strategies for Federated Semantic Communications in Heterogeneous IoT Networks
The exponential growth of IoT devices presents critical challenges in bandwidth-constrained wireless networks, particularly regarding efficient data transmission and privacy preservation. This paper presents a novel federated semantic communication (SC) framework that enables collaborative training of bandwidth-efficient models for image reconstruction across heterogeneous IoT devices. By leveraging SC principles to transmit only semantic features, our approach dramatically reduces communicatio…

Modeling and Visualization Reasoning for Stakeholders in Education and Industry Integration Systems: Research on Structured Synthetic Dialogue Data Generation Based on NIST Standards
Wei Meng
https://arxiv.org/abs/2506.16952

Modeling and Visualization Reasoning for Stakeholders in Education and Industry Integration Systems: Research on Structured Synthetic Dialogue Data Generation Based on NIST Standards
This study addresses the structural complexity and semantic ambiguity in stakeholder interactions within the Education-Industry Integration (EII) system. The scarcity of real interview data, absence of structured variable modeling, and lack of interpretability in inference mechanisms have limited the analytical accuracy and policy responsiveness of EII research. To resolve these challenges, we propose a structural modeling paradigm based on the National Institute of Standards and Technology (NI…

Decompiling Smart Contracts with a Large Language Model
Isaac David, Liyi Zhou, Dawn Song, Arthur Gervais, Kaihua Qin
https://arxiv.org/abs/2506.19624 http…

Decompiling Smart Contracts with a Large Language Model
The widespread lack of broad source code verification on blockchain explorers such as Etherscan, where despite 78,047,845 smart contracts deployed on Ethereum (as of May 26, 2025), a mere 767,520 (< 1%) are open source, presents a severe impediment to blockchain security. This opacity necessitates the automated semantic analysis of on-chain smart contract bytecode, a fundamental research challenge with direct implications for identifying vulnerabilities and understanding malicious behavior. Pre…

Semantic Communications in 6G: Coexistence, Multiple Access, and Satellite Networks
Ishtiaque Ahmed, Yingzhuo Sun, Jingwen Fu, Alper Kose, Leila Musavian, Ming Xiao, Berna Ozbek
https://arxiv.org/abs/2506.11779

Semantic Communications in 6G: Coexistence, Multiple Access, and Satellite Networks
The exponential growth of wireless users and bandwidth constraints necessitates innovative communication paradigms for next-generation networks. Semantic Communication (SemCom) emerges as a promising solution by transmitting extracted meaning rather than raw bits, enhancing spectral efficiency and enabling intelligent resource allocation. This paper explores the integration of SemCom with conventional Bit-based Communication (BitCom) in heterogeneous networks, highlighting key challenges and op…

Redefining Functionality and Construction-Defining Capacity: Functions as Principles of Syntactic and Semantic Generation
Yumiko Nishiyama
https://arxiv.org/abs/2506.04278

Redefining Functionality and Construction-Defining Capacity: Functions as Principles of Syntactic and Semantic Generation
This study redefines the notion of functionality-traditionally understood as a property of mappings or structure preservation-from a more fundamental and generative perspective. Introducing the concept of a Construction-Defining function (CDF), we formalize functionality as a dual capacity to generate both syntactic terms and semantic interpretations. We provide an explicit axiomatization of CDF based on syntactic generativity and semantic compositionality, and further construct categorical mod…

Machine Mirages: Defining the Undefined
Hamidou Tembine
https://arxiv.org/abs/2506.13990 https://arxiv.org/pdf/2506.13990

Machine Mirages: Defining the Undefined
As multimodal machine intelligence systems started achieving average animal-level and average human-level fluency in many measurable tasks in processing images, language, and sound, they began to exhibit a new class of cognitive aberrations: machine mirages. These include delusion, illusion, confabulation, hallucination, misattribution error, semantic drift, semantic compression, exaggeration, causal inference failure, uncanny valley of perception, bluffing-patter-bullshitting, cognitive stereo…

SEED: A Structural Encoder for Embedding-Driven Decoding in Time Series Prediction with LLMs
Fengze Li, Yue Wang, Yangle Liu, Ming Huang, Dou Hong, Jieming Ma
https://arxiv.org/abs/2506.20167

SEED: A Structural Encoder for Embedding-Driven Decoding in Time Series Prediction with LLMs
Multivariate time series forecasting requires models to simultaneously capture variable-wise structural dependencies and generalize across diverse tasks. While structural encoders are effective in modeling feature interactions, they lack the capacity to support semantic-level reasoning or task adaptation. Conversely, large language models (LLMs) possess strong generalization capabilities but remain incompatible with raw time series inputs. This gap limits the development of unified, transferabl…

SlimRAG: Retrieval without Graphs via Entity-Aware Context Selection
Jiale Zhang, Jiaxiang Chen, Zhucong Li, Jie Ding, Kui Zhao, Zenglin Xu, Xin Pang, Yinghui Xu
https://arxiv.org/abs/2506.17288

SlimRAG: Retrieval without Graphs via Entity-Aware Context Selection
Retrieval-Augmented Generation (RAG) enhances language models by incorporating external knowledge at inference time. However, graph-based RAG systems often suffer from structural overhead and imprecise retrieval: they require costly pipelines for entity linking and relation extraction, yet frequently return subgraphs filled with loosely related or tangential content. This stems from a fundamental flaw -- semantic similarity does not imply semantic relevance. We introduce SlimRAG, a lightweight …

When concept-based XAI is imprecise: Do people distinguish between generalisations and misrepresentations?
Romy M\"uller
https://arxiv.org/abs/2506.17936

When concept-based XAI is imprecise: Do people distinguish between generalisations and misrepresentations?
Concept-based explainable artificial intelligence (C-XAI) can help reveal the inner representations of AI models. Understanding these representations is particularly important in complex tasks like safety evaluation. Such tasks rely on high-level semantic information (e.g., about actions) to make decisions about abstract categories (e.g., whether a situation is dangerous). In this context, it may desirable for C-XAI concepts to show some variability, suggesting that the AI is capable of general…

Taming Vision-Language Models for Medical Image Analysis: A Comprehensive Review
Haoneng Lin, Cheng Xu, Jing Qin
https://arxiv.org/abs/2506.18378 https://

Taming Vision-Language Models for Medical Image Analysis: A Comprehensive Review
Modern Vision-Language Models (VLMs) exhibit unprecedented capabilities in cross-modal semantic understanding between visual and textual modalities. Given the intrinsic need for multi-modal integration in clinical applications, VLMs have emerged as a promising solution for a wide range of medical image analysis tasks. However, adapting general-purpose VLMs to medical domain poses numerous challenges, such as large domain gaps, complicated pathological variations, and diversity and uniqueness of…

WebGuard :Interpretable Malicious URL Detection via Bidirectional Fusion of HTML Subgraphs and Multi-Scale Convolutional BERT
Ye Tian, Zhang Yumin, Yifan Jia, Jianguo Sun, Yanbin Wang
https://arxiv.org/abs/2506.19356

WebGuard++:Interpretable Malicious URL Detection via Bidirectional Fusion of HTML Subgraphs and Multi-Scale Convolutional BERT
URL+HTML feature fusion shows promise for robust malicious URL detection, since attacker artifacts persist in DOM structures. However, prior work suffers from four critical shortcomings: (1) incomplete URL modeling, failing to jointly capture lexical patterns and semantic context; (2) HTML graph sparsity, where threat-indicative nodes (e.g., obfuscated scripts) are isolated amid benign content, causing signal dilution during graph aggregation; (3) unidirectional analysis, ignoring URL-HTML feat…

Semantic Communication for Cooperative Multi-Tasking over Rate-Limited Wireless Channels with Implicit Optimal Prior
Ahmad Halimi Razlighi, Carsten Bockelmann, Armin Dekorsy
https://arxiv.org/abs/2506.08944

Semantic Communication for Cooperative Multi-Tasking over Rate-Limited Wireless Channels with Implicit Optimal Prior
In this work, we expand the cooperative multi-task semantic communication framework (CMT-SemCom) introduced in [1], which divides the semantic encoder on the transmitter side into a common unit (CU) and multiple specific units (SUs), to a more applicable design. Our proposed system model addresses real-world constraints by introducing a general design that operates over rate-limited wireless channels. Further, we aim to tackle the rate-limit constraint, represented through the Kullback-Leibler …

Distributed Image Semantic Communication via Nonlinear Transform Coding
Yufei Bo, Meixia Tao, Kai Niu
https://arxiv.org/abs/2506.07391 https://

Distributed Image Semantic Communication via Nonlinear Transform Coding
This paper investigates distributed source-channel coding for correlated image semantic transmission over wireless channels. In this setup, correlated images at different transmitters are separately encoded and transmitted through dedicated channels for joint recovery at the receiver. We propose a general approach for distributed image semantic communication that applies to both separate source and channel coding (SSCC) and joint source-channel coding (JSCC). Unlike existing learning-based appr…

jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval
Michael G\"unther, Saba Sturua, Mohammad Kalim Akram, Isabelle Mohr, Andrei Ungureanu, Sedigheh Eslami, Scott Martens, Bo Wang, Nan Wang, Han Xiao
https://arxiv.org/abs/2506.18902

jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval
We introduce jina-embeddings-v4, a 3.8 billion parameter multimodal embedding model that unifies text and image representations through a novel architecture supporting both single-vector and multi-vector embeddings in the late interaction style. The model incorporates task-specific Low-Rank Adaptation (LoRA) adapters to optimize performance across diverse retrieval scenarios, including query-based information retrieval, cross-modal semantic similarity, and programming code search. Comprehensive…

Efficient Manipulation-Enhanced Semantic Mapping With Uncertainty-Informed Action Selection
Nils Dengler, Jesper M\"ucke, Rohit Menon, Maren Bennewitz
https://arxiv.org/abs/2506.02286

Efficient Manipulation-Enhanced Semantic Mapping With Uncertainty-Informed Action Selection
Service robots operating in cluttered human environments such as homes, offices, and schools cannot rely on predefined object arrangements and must continuously update their semantic and spatial estimates while dealing with possible frequent rearrangements. Efficient and accurate mapping under such conditions demands selecting informative viewpoints and targeted manipulations to reduce occlusions and uncertainty. In this work, we present a manipulation-enhanced semantic mapping framework for oc…

MERIT: Multilingual Semantic Retrieval with Interleaved Multi-Condition Query
Wei Chow, Yuan Gao, Linfeng Li, Xian Wang, Qi Xu, Hang Song, Lingdong Kong, Ran Zhou, Yi Zeng, Yidong Cai, Botian Jiang, Shilin Xu, Jiajun Zhang, Minghui Qiu, Xiangtai Li, Tianshu Yang, Siliang Tang, Juncheng Li
https://arxiv.org/abs/2506.03144

MERIT: Multilingual Semantic Retrieval with Interleaved Multi-Condition Query
Semantic retrieval is crucial for modern applications yet remains underexplored in current research. Existing datasets are limited to single languages, single images, or singular retrieval conditions, often failing to fully exploit the expressive capacity of visual information as evidenced by maintained performance when images are replaced with captions. However, practical retrieval scenarios frequently involve interleaved multi-condition queries with multiple images. Hence, this paper introduc…

Description and Discussion on DCASE 2025 Challenge Task 4: Spatial Semantic Segmentation of Sound Scenes
Masahiro Yasuda, Binh Thien Nguyen, Noboru Harada, Romain Serizel, Mayank Mishra, Marc Delcroix, Shoko Araki, Daiki Takeuchi, Daisuke Niizumi, Yasunori Ohishi, Tomohiro Nakatani, Takao Kawamura, Nobutaka Ono
https://arxiv.org…

Description and Discussion on DCASE 2025 Challenge Task 4: Spatial Semantic Segmentation of Sound Scenes
Spatial Semantic Segmentation of Sound Scenes (S5) aims to enhance technologies for sound event detection and separation from multi-channel input signals that mix multiple sound events with spatial information. This is a fundamental basis of immersive communication. The ultimate goal is to separate sound event signals with 6 Degrees of Freedom (6DoF) information into dry sound object signals and metadata about the object type (sound event class) and representing spatial information, including d…

Neural Prioritisation for Web Crawling
Francesza Pezzuti, Sean MacAvaney, Nicola Tonellotto
https://arxiv.org/abs/2506.16146 https://…

Neural Prioritisation for Web Crawling
Given the vast scale of the Web, crawling prioritisation techniques based on link graph traversal, popularity, link analysis, and textual content are frequently applied to surface documents that are most likely to be valuable. While existing techniques are effective for keyword-based search, both retrieval methods and user search behaviours are shifting from keyword-based matching to natural language semantic matching. The remarkable success of applying semantic matching and quality signals dur…

Proceedings of the 19th International Workshop on Logical and Semantic Frameworks, with Applications
Cynthia Kop (Radboud Universiteit Nijmegen), Helida Salles Santos (Universidade Federal do Rio Grande)
https://arxiv.org/abs/2506.05219

Proceedings of the 19th International Workshop on Logical and Semantic Frameworks, with Applications
This volume contains the post-proceedings of the 19th LSFA, which was held in Goiânia, the capital of Goiás state in Brazil, from September 18 to September 20, 2024. Logical and semantic frameworks are formal languages used to represent logics, languages and systems. These frameworks provide foundations for the formal specification of systems and programming languages, supporting tool development and reasoning. The aim of this series is bringing together theoreticians and practitioners t…

AST-Enhanced or AST-Overloaded? The Surprising Impact of Hybrid Graph Representations on Code Clone Detection
Zixian Zhang, Takfarinas Saber
https://arxiv.org/abs/2506.14470

AST-Enhanced or AST-Overloaded? The Surprising Impact of Hybrid Graph Representations on Code Clone Detection
As one of the most detrimental code smells, code clones significantly increase software maintenance costs and heighten vulnerability risks, making their detection a critical challenge in software engineering. Abstract Syntax Trees (ASTs) dominate deep learning-based code clone detection due to their precise syntactic structure representation, but they inherently lack semantic depth. Recent studies address this by enriching AST-based representations with semantic graphs, such as Control Flow Gra…

Join Radu Pop and Pietro Mele at Berlin Buzzwords as they discuss building an extensible hybrid search solution with Elasticsearch. They will cover functional modeling, cluster architecture, and practical insights on managing billions of vectors in real-world scenarios. Radu and Pietro will also address hybrid reranking challenges and the limitations of standard fusion techniques, explaining their innovative approach.
Learn more:

Alphabet Index Mapping: Jailbreaking LLMs through Semantic Dissimilarity
Bilal Saleh Husain
https://arxiv.org/abs/2506.12685 https://…

Alphabet Index Mapping: Jailbreaking LLMs through Semantic Dissimilarity
Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their susceptibility to adversarial attacks, particularly jailbreaking, poses significant safety and ethical concerns. While numerous jailbreak methods exist, many suffer from computational expense, high token usage, or complex decoding schemes. Liu et al. (2024) introduced FlipAttack, a black-box method that achieves high attack success rates (ASR) through simple prompt manipulation. This paper investigates the underly…

MTSIC: Multi-stage Transformer-based GAN for Spectral Infrared Image Colorization
Tingting Liu, Yuan Liu, Jinhui Tang, Liyin Yuan, Chengyu Liu, Chunlai Li, Xiubao Sui, Qian Chen
https://arxiv.org/abs/2506.17540

MTSIC: Multi-stage Transformer-based GAN for Spectral Infrared Image Colorization
Thermal infrared (TIR) images, acquired through thermal radiation imaging, are unaffected by variations in lighting conditions and atmospheric haze. However, TIR images inherently lack color and texture information, limiting downstream tasks and potentially causing visual fatigue. Existing colorization methods primarily rely on single-band images with limited spectral information and insufficient feature extraction capabilities, which often result in image distortion and semantic ambiguity. In …

When Does Meaning Backfire? Investigating the Role of AMRs in NLI
Junghyun Min, Xiulin Yang, Shira Wein
https://arxiv.org/abs/2506.14613 https://

When Does Meaning Backfire? Investigating the Role of AMRs in NLI
Natural Language Inference (NLI) relies heavily on adequately parsing the semantic content of the premise and hypothesis. In this work, we investigate whether adding semantic information in the form of an Abstract Meaning Representation (AMR) helps pretrained language models better generalize in NLI. Our experiments integrating AMR into NLI in both fine-tuning and prompting settings show that the presence of AMR in fine-tuning hinders model generalization while prompting with AMR leads to sligh…

Optimization for Semantic-Aware Resource Allocation under CPT-based Utilities
Symeon Vaidanis, Photios A. Stavrou, Marios Kountouris
https://arxiv.org/abs/2506.04952

Optimization for Semantic-Aware Resource Allocation under CPT-based Utilities
The problem of resource allocation in goal-oriented semantic communication with semantic-aware utilities and subjective risk perception is studied here. By linking information importance to risk aversion, we model agent behavior using Cumulative Prospect Theory (CPT), which incorporates risk-sensitive utility functions and nonlinear transformations of distributions, reflecting subjective perceptions of gains and losses. The objective is to maximize the aggregate utility across multiple CPT-mode…

CodeDiffuser: Attention-Enhanced Diffusion Policy via VLM-Generated Code for Instruction Ambiguity
Guang Yin, Yitong Li, Yixuan Wang, Dale McConachie, Paarth Shah, Kunimatsu Hashimoto, Huan Zhang, Katherine Liu, Yunzhu Li
https://arxiv.org/abs/2506.16652

CodeDiffuser: Attention-Enhanced Diffusion Policy via VLM-Generated Code for Instruction Ambiguity
Natural language instructions for robotic manipulation tasks often exhibit ambiguity and vagueness. For instance, the instruction "Hang a mug on the mug tree" may involve multiple valid actions if there are several mugs and branches to choose from. Existing language-conditioned policies typically rely on end-to-end models that jointly handle high-level semantic understanding and low-level action generation, which can result in suboptimal performance due to their lack of modularity and interpret…

This https://arxiv.org/abs/2412.03283 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Models
Integrating watermarking into the generation process of latent diffusion models (LDMs) simplifies detection and attribution of generated content. Semantic watermarks, such as Tree-Rings and Gaussian Shading, represent a novel class of watermarking techniques that are easy to implement and highly robust against various perturbations. However, our work demonstrates a fundamental security vulnerability of semantic watermarks. We show that attackers can leverage unrelated models, even with differen…

Agentic Semantic Control for Autonomous Wireless Space Networks: Extending Space-O-RAN with MCP-Driven Distributed Intelligence
Eduardo Baena, Paolo Testolina, Michele Polese, Sergi Aliaga, Andrew Benincasa, Dimitrios Koutsonikolas, Josep Jornet, Tommaso Melodia
https://arxiv.org/abs/2506.10925

Agentic Semantic Control for Autonomous Wireless Space Networks: Extending Space-O-RAN with MCP-Driven Distributed Intelligence
Lunar surface operations impose stringent requirements on wireless communication systems, including autonomy, robustness to disruption, and the ability to adapt to environmental and mission-driven context. While Space-O-RAN provides a distributed orchestration model aligned with 3GPP standards, its decision logic is limited to static policies and lacks semantic integration. We propose a novel extension incorporating a semantic agentic layer enabled by the Model Context Protocol (MCP) and Agent-…

Generating Long Semantic IDs in Parallel for Recommendation
Yupeng Hou, Jiacheng Li, Ashley Shin, Jinsung Jeon, Abhishek Santhanam, Wei Shao, Kaveh Hassani, Ning Yao, Julian McAuley
https://arxiv.org/abs/2506.05781

Generating Long Semantic IDs in Parallel for Recommendation
Semantic ID-based recommendation models tokenize each item into a small number of discrete tokens that preserve specific semantics, leading to better performance, scalability, and memory efficiency. While recent models adopt a generative approach, they often suffer from inefficient inference due to the reliance on resource-intensive beam search and multiple forward passes through the neural sequence model. As a result, the length of semantic IDs is typically restricted (e.g. to just 4 tokens), …

CLEAR-3K: Assessing Causal Explanatory Capabilities in Language Models
Naiming Liu, Richard Baraniuk, Shashank Sonkar
https://arxiv.org/abs/2506.17180 http…

CLEAR-3K: Assessing Causal Explanatory Capabilities in Language Models
We introduce CLEAR-3K, a dataset of 3,000 assertion-reasoning questions designed to evaluate whether language models can determine if one statement causally explains another. Each question present an assertion-reason pair and challenge language models to distinguish between semantic relatedness and genuine causal explanatory relationships. Through comprehensive evaluation of 21 state-of-the-art language models (ranging from 0.5B to 72B parameters), we identify two fundamental findings. First, l…

A Simple but Accurate Approximation for Multivariate Gaussian Rate-Distortion Function and Its Application in Maximal Coding Rate Reduction
Zhenglin Huang, Qifa Yan, Bin Dai, Xiaohu Tang
https://arxiv.org/abs/2506.18613

A Simple but Accurate Approximation for Multivariate Gaussian Rate-Distortion Function and Its Application in Maximal Coding Rate Reduction
The multivariate Gaussian rate-distortion (RD) function is crucial in various applications, such as digital communications, data storage, or neural networks. However, the complex form of the multivariate Gaussian RD function prevents its application in many neural network-based scenarios that rely on its analytical properties, for example, white-box neural networks, multi-device task-oriented communication, and semantic communication. This paper proposes a simple but accurate approximation for …

Obfuscation-Resilient Binary Code Similarity Analysis using Dominance Enhanced Semantic Graph
Yufeng Wang, Yuhong Feng, Yixuan Cao, Haoran Li, Haiyue Feng, Yifeng Wang
https://arxiv.org/abs/2506.06161

Obfuscation-Resilient Binary Code Similarity Analysis using Dominance Enhanced Semantic Graph
Binary code similarity analysis (BCSA) serves as a core technique for binary analysis tasks such as vulnerability detection. While current graph-based BCSA approaches capture substantial semantics and show strong performance, their performance suffers under code obfuscation due to the unstable control flow. To address this issue, we develop ORCAS, an Obfuscation-Resilient BCSA model based on Dominance Enhanced Semantic Graph (DESG). The DESG is an original binary code representation, capturing …

Generative Next POI Recommendation with Semantic ID
Dongsheng Wang, Yuxi Huang, Shen Gao, Yifan Wang, Chengrui Huang, Shuo Shang
https://arxiv.org/abs/2506.01375

Generative Next POI Recommendation with Semantic ID
Point-of-interest (POI) recommendation systems aim to predict the next destinations of user based on their preferences and historical check-ins. Existing generative POI recommendation methods usually employ random numeric IDs for POIs, limiting the ability to model semantic relationships between similar locations. In this paper, we propose Generative Next POI Recommendation with Semantic ID (GNPR-SID), an LLM-based POI recommendation model with a novel semantic POI ID (SID) representation metho…

SmartGuard: Leveraging Large Language Models for Network Attack Detection through Audit Log Analysis and Summarization
Hao Zhang, Shuo Shao, Song Li, Zhenyu Zhong, Yan Liu, Zhan Qin, Kui Ren
https://arxiv.org/abs/2506.16981

SmartGuard: Leveraging Large Language Models for Network Attack Detection through Audit Log Analysis and Summarization
End-point monitoring solutions are widely deployed in today's enterprise environments to support advanced attack detection and investigation. These monitors continuously record system-level activities as audit logs and provide deep visibility into security events. Unfortunately, existing methods of semantic analysis based on audit logs have low granularity, only reaching the system call level, making it difficult to effectively classify highly covert behaviors. Additionally, existing works main…

Harnessing the Power of Reinforcement Learning for Language-Model-Based Information Retriever via Query-Document Co-Augmentation
Jingming Liu, Yumeng Li, Wei Shi, Yao-Xiang Ding, Hui Su, Kun Zhou
https://arxiv.org/abs/2506.18670

Harnessing the Power of Reinforcement Learning for Language-Model-Based Information Retriever via Query-Document Co-Augmentation
Recent studies have proposed leveraging Large Language Models (LLMs) as information retrievers through query rewriting. However, for challenging corpora, we argue that enhancing queries alone is insufficient for robust semantic matching; the LLM should also have sufficient understanding of the corpus by directly handling and augmenting the documents themselves. To this end, we present an LLM-based retriever empowered to augment both user queries and corpus documents, with its policy fully explo…

A GenAI System for Improved FAIR Independent Biological Database Integration
Syed N. Sakib, Kallol Naha, Sajratul Y. Rubaiat, Hasan M. Jamil
https://arxiv.org/abs/2506.17934

A GenAI System for Improved FAIR Independent Biological Database Integration
Life sciences research increasingly requires identifying, accessing, and effectively processing data from an ever-evolving array of information sources on the Linked Open Data (LOD) network. This dynamic landscape places a significant burden on researchers, as the quality of query responses depends heavily on the selection and semantic integration of data sources --processes that are often labor-intensive, error-prone, and costly. While the adoption of FAIR (Findable, Accessible, Interoperable,…

Similarity = Value? Consultation Value Assessment and Alignment for Personalized Search
Weicong Qin, Yi Xu, Weijie Yu, Teng Shi, Chenglei Shen, Ming He, Jianping Fan, Xiao Zhang, Jun Xu
https://arxiv.org/abs/2506.14437

Similarity = Value? Consultation Value Assessment and Alignment for Personalized Search
Personalized search systems in e-commerce platforms increasingly involve user interactions with AI assistants, where users consult about products, usage scenarios, and more. Leveraging consultation to personalize search services is trending. Existing methods typically rely on semantic similarity to align historical consultations with current queries due to the absence of 'value' labels, but we observe that semantic similarity alone often fails to capture the true value of consultation for perso…

GLoSS: Generative Language Models with Semantic Search for Sequential Recommendation
Krishna Acharya, Aleksandr V. Petrov, Juba Ziani
https://arxiv.org/abs/2506.01910

GLoSS: Generative Language Models with Semantic Search for Sequential Recommendation
We propose Generative Low-rank language model with Semantic Search (GLoSS), a generative recommendation framework that combines large language models with dense retrieval for sequential recommendation. Unlike prior methods such as GPT4Rec, which rely on lexical matching via BM25, GLoSS uses semantic search to retrieve relevant items beyond lexical matching. For query generation, we employ 4-bit quantized LlaMA-3 models fine-tuned with low-rank adaptation (LoRA), enabling efficient training and …

Optimizing Question Semantic Space for Dynamic Retrieval-Augmented Multi-hop Question Answering
Linhao Ye, Lang Yu, Zhikai Lei, Qin Chen, Jie Zhou, Liang He
https://arxiv.org/abs/2506.00491

Optimizing Question Semantic Space for Dynamic Retrieval-Augmented Multi-hop Question Answering
Retrieval-augmented generation (RAG) is usually integrated into large language models (LLMs) to mitigate hallucinations and knowledge obsolescence. Whereas,conventional one-step retrieve-and-read methods are insufficient for multi-hop question answering, facing challenges of retrieval semantic mismatching and the high cost in handling interdependent subquestions. In this paper, we propose Optimizing Question Semantic Space for Dynamic Retrieval-Augmented Multi-hop Question Answering (Q-DREAM). …