Tootfinder

One Sentence, Two Embeddings: Contrastive Learning of Explicit and Implicit Semantic Representations
Kohei Oda, Po-Min Chuang, Kiyoaki Shirai, Natthawut Kertkeidkachorn
https://arxiv.org/abs/2510.09293

One Sentence, Two Embeddings: Contrastive Learning of Explicit and Implicit Semantic Representations
Sentence embedding methods have made remarkable progress, yet they still struggle to capture the implicit semantics within sentences. This can be attributed to the inherent limitations of conventional sentence embedding methods that assign only a single vector per sentence. To overcome this limitation, we propose DualCSE, a sentence embedding method that assigns two embeddings to each sentence: one representing the explicit semantics and the other representing the implicit semantics. These embe…

Semantic-Condition Tuning: Fusing Graph Context with Large Language Models for Knowledge Graph Completion
Ruitong Liu, Yan Wen, Te Sun, Yunjia Wu, Pingyang Huang, Zihang Yu, Siyuan Li
https://arxiv.org/abs/2510.08966

Semantic-Condition Tuning: Fusing Graph Context with Large Language Models for Knowledge Graph Completion
Fusing Knowledge Graphs with Large Language Models is crucial for knowledge-intensive tasks like knowledge graph completion. The prevailing paradigm, prefix-tuning, simply concatenates knowledge embeddings with text inputs. However, this shallow fusion overlooks the rich relational semantics within KGs and imposes a significant implicit reasoning burden on the LLM to correlate the prefix with the text. To address these, we propose Semantic-condition Tuning (SCT), a new knowledge injection parad…

Personalize Before Retrieve: LLM-based Personalized Query Expansion for User-Centric Retrieval
Yingyi Zhang, Pengyue Jia, Derong Xu, Yi Wen, Xianneng Li, Yichao Wang, Wenlin Zhang, Xiaopeng Li, Weinan Gan, Huifeng Guo, Yong Liu, Xiangyu Zhao
https://arxiv.org/abs/2510.08935

Personalize Before Retrieve: LLM-based Personalized Query Expansion for User-Centric Retrieval
Retrieval-Augmented Generation (RAG) critically depends on effective query expansion to retrieve relevant information. However, existing expansion methods adopt uniform strategies that overlook user-specific semantics, ignoring individual expression styles, preferences, and historical context. In practice, identical queries in text can express vastly different intentions across users. This representational rigidity limits the ability of current RAG systems to generalize effectively in personali…

We are happy to welcome @… from RWTH in today's #nfdicore playground talking about "Bridging the Gap from Biomedical to Domain-Agnostic Semantics".
Besides others, he is demonstrating that our

A cool open source UI component library, but a lot of them I looked at don't have good semantics or accessibility compliance. #webdevelopment

Free to Move: Reachability Types with Flow-Sensitive Effects for Safe Deallocation and Ownership Transfer
Haotian Deng, Siyuan He, Songlin Jia, Yuyan Bao, Tiark Rompf
https://arxiv.org/abs/2510.08939

Free to Move: Reachability Types with Flow-Sensitive Effects for Safe Deallocation and Ownership Transfer
We present a flow-sensitive effect system for reachability types that supports explicit memory management, including Rust-style move semantics, in higher-order impure functional languages. Our system refines the existing reachability qualifier with polymorphic \emph{use} and \emph{kill} effects that record how references are read, written, transferred, and deallocated. The effect discipline tracks operations performed on each resource using qualifiers, enabling the type system to express owners…

I wasn't surprised to see Rob Sanderson quoted in this, because rich vs aligned semantics - specifically , wanting both at the same time - is *such* a cultural heritage data interoperability problem #MuseTech
From: @…

Pieter Colpaert (@pietercolpaert@mastodon.social)
Attached: 2 images There’s a tension between being semantically rich (using your own terms and definitions), and being semantically aligned, in which you try to reuse terms from other vocabularies. I think we need a new concept: eventual #interoperability. I propose to start rich with your own vocabularies, and only make alignments when there’s a concrete reason for building those. https://pietercolpaert.be/interoperability/2026/01/08/eventual-interoperability #knowledgegraphs #apis #li…

Hierarchical Indexing with Knowledge Enrichment for Multilingual Video Corpus Retrieval
Yu Wang, Tianhao Tan, Yifei Wang
https://arxiv.org/abs/2510.09553 https://

Hierarchical Indexing with Knowledge Enrichment for Multilingual Video Corpus Retrieval
Retrieving relevant instructional videos from multilingual medical archives is crucial for answering complex, multi-hop questions across language boundaries. However, existing systems either compress hour-long videos into coarse embeddings or incur prohibitive costs for fine-grained matching. We tackle the Multilingual Video Corpus Retrieval (mVCR) task in the NLPCC-2025 M4IVQA challenge with a multi-stage framework that integrates multilingual semantics, domain terminology, and efficient long-…

OpenAI and Perplexity, armed with significant AI capabilities, have targeted the shopping domain. And have run into many problems around data access and semantics.
This raises three thoughts:
First, companies which are bullish about AI “changing everything”, are stumbling in maybe the most traditional, mundane domain: shopping. This doesn’t inspire confidence in their technology.
1/5
#ai

A cool open source UI component library, but a lot of them I looked at don't have good semantics or accessibility compliance. #webdevelopment

https://www.theguardian.com/politics/2025/oct/13/muddle-over-semantics-or-pressure-from-china-collapsed-spying-case-remains-baffling
Muddle over semantics or pressure from China? Collapsed spying…

Ana Tudor rolling into the comments with corrections and useful #CSS values context (trousers!):
https://css-tricks.com/headings-semantics-fluidity-and-styling-oh-my/#…

Headings: Semantics, Fluidity, and Styling — Oh My! | CSS-Tricks
A few links about headings that I've had stored under my top hat.

Revised comment on the paper titled "The Origin of Quantum Mechanical Statistics: Insights from Research on Human Language
Miko{\l}aj Sienicki, Krzysztof Sienicki
https://arxiv.org/abs/2512.07881 https://arxiv.org/pdf/2512.07881 https://arxiv.org/html/2512.07881
arXiv:2512.07881v1 Announce Type: new
Abstract: This short note comments on \citet{Aerts2024Origin}, which proposes that ranked word frequencies in texts should be read through the lens of Bose--Einstein (BE) statistics and even used to illuminate the origin of quantum statistics in physics. The core message here is modest: the paper offers an interesting analogy and an eye-catching fit, but several key steps mix physical claims with definitions and curve-fitting choices. We highlight three such points: (i) a normalization issue that is presented as "bosonic enhancement", (ii) an identification of rank with energy that makes the BE fit only weakly diagnostic of an underlying mechanism, and (iii) a baseline comparison that is too weak to support an ontological conclusion. We also briefly flag a few additional concerns (interpretation drift, parameter semantics, and reproducibility).
toXiv_bot_toot

Brain-aligning of semantic vectors improves neural decoding of visual stimuli #BCI

Syntax is not Semantics
Language is not the same as intelligence.
The entire AI bubble is built on ignoring that.
https://www.theverge.com/ai-artificial-intelligence/827820/large-language-models-ai-intellige…

Large language mistake
Neuroscience indicates language is distinct from thought, raising questions about whether AI large language models are a viable path to artificial general intelligence.

#IsraelIsATerroristState

Historians: Quibbling Over Exact Definition Of Concentration Camp Sign Of Healthy Society
NEW HAVEN, CT—Calling such concern for linguistic precision a clear indicator of a thriving country, a panel of historians from Yale University issued a statement Thursday announcing that quibbling over the exact definition of a concentration camp was a sign of a healthy society. “Studies of the past tell us that nitpicking the particular semantics […]

Operational methods in semantics
Roberto M. Amadio
https://arxiv.org/abs/2510.12295 https://arxiv.org/pdf/2510.12295

Operational methods in semantics
The focus of these lecture notes is on abstract models and basic ideas and results that relate to the operational semantics of programming languages largely conceived. The approach is to start with an abstract description of the computation steps of programs and then to build on top semantic equivalences, specification languages, and static analyses. While other approaches to the semantics of programming languages are possible, it appears that the operational one is particularly effective in th…

Bridging Semantics & Structure for Software Vulnerability Detection using Hybrid Network Models
Jugal Gajjar, Kaustik Ranaware, Kamalasankari Subramaniakuppusamy
https://arxiv.org/abs/2510.10321

Bridging Semantics & Structure for Software Vulnerability Detection using Hybrid Network Models
Software vulnerabilities remain a persistent risk, yet static and dynamic analyses often overlook structural dependencies that shape insecure behaviors. Viewing programs as heterogeneous graphs, we capture control- and data-flow relations as complex interaction networks. Our hybrid framework combines these graph representations with light-weight (<4B) local LLMs, uniting topological features with semantic reasoning while avoiding the cost and privacy concerns of large cloud models. Evaluated on…

Oh no, #Intel platform detection isn't that easy.
There is no simple field like platform ID or something in #IFD to determine it.
Also, IFD fields have changes semantics a bit over time.
So #coreboot

coreboot/util/ifdtool/ifdtool.c at 19feafc018f1b0f5184edd6bf4b4b068ef190dab · coreboot/coreboot
Read-only mirror of https://review.coreboot.org/coreboot.git. Synced every hour. We don't handle Pull Requests. - coreboot/coreboot

Scott helpfully reminds us of the differences between technical purity, semantics, and what actually matters to users in the context of — yes, really — paragraphs:
https://www.scottohara.me/blog/2024/08/29/paragraphs.html

🚨 Yesterday, I received official notification that our #emoji project EmDiCom is being funded for another three years! 🥳
I'm looking forward to a lot more 🤩 emoji research 🤩 together with Patrick Grosz and Lea Fricke! #linguistics #dfg #vicom @… https://vicom.info/projects/semantics-and-pragmatics-of-emojis-in-digital-communication/

KoALA: KL-L0 Adversarial Detector via Label Agreement
Siqi Li, Yasser Shoukry
https://arxiv.org/abs/2510.12752 https://arxiv.org/pdf/2510.12752

KoALA: KL-L0 Adversarial Detector via Label Agreement
Deep neural networks are highly susceptible to adversarial attacks, which pose significant risks to security- and safety-critical applications. We present KoALA (KL-L0 Adversarial detection via Label Agreement), a novel, semantics-free adversarial detector that requires no architectural changes or adversarial retraining. KoALA operates on a simple principle: it detects an adversarial attack when class predictions from two complementary similarity metrics disagree. These metrics-KL divergence an…

FACE: Faithful Automatic Concept Extraction
Dipkamal Bhusal, Michael Clifford, Sara Rampazzi, Nidhi Rastogi
https://arxiv.org/abs/2510.11675 https://arxiv.…

FACE: Faithful Automatic Concept Extraction
Interpreting deep neural networks through concept-based explanations offers a bridge between low-level features and high-level human-understandable semantics. However, existing automatic concept discovery methods often fail to align these extracted concepts with the model's true decision-making process, thereby compromising explanation faithfulness. In this work, we propose FACE (Faithful Automatic Concept Extraction), a novel framework that augments Non-negative Matrix Factorization (NMF) with…

Crosslisted article(s) found for cs.LO. https://arxiv.org/list/cs.LO/new
[1/1]:
- Operational methods in semantics
Roberto M. Amadio
https://

Leveraging Language Semantics for Collaborative Filtering with TextGCN and TextGCN-MLP: Zero-Shot vs In-Domain Performance
Andrei Chernov, Haroon Wahab, Oleg Novitskij
https://arxiv.org/abs/2510.12461 …

Leveraging Language Semantics for Collaborative Filtering with TextGCN and TextGCN-MLP: Zero-Shot vs In-Domain Performance
In recent years, various approaches have been proposed to leverage large language models (LLMs) for incorporating textual information about items into recommender systems. Existing methods primarily focus on either fine-tuning LLMs to generate recommendations or integrating LLM-based embeddings into downstream models. In this work, we follow the latter direction and propose \textbf{TextGCN}, which applies parameter-free graph convolution layers directly over LLM-based item-title embeddings, ins…

GrASP: A Generalizable Address-based Semantic Prefetcher for Scalable Transactional and Analytical Workloads
Farzaneh Zirak, Farhana Choudhury, Renata Borovica-Gajic
https://arxiv.org/abs/2510.11011

GrASP: A Generalizable Address-based Semantic Prefetcher for Scalable Transactional and Analytical Workloads
Data prefetching--loading data into the cache before it is requested--is essential for reducing I/O overhead and improving database performance. While traditional prefetchers focus on sequential patterns, recent learning-based approaches, especially those leveraging data semantics, achieve higher accuracy for complex access patterns. However, these methods often struggle with today's dynamic, ever-growing datasets and require frequent, timely fine-tuning. Privacy constraints may also restrict a…

Can Representation Gaps Be the Key to Enhancing Robustness in Graph-Text Alignment?
Heng Zhang, Tianyi Zhang, Yuling Shi, Xiaodong Gu, Yaomin Shen, Zijian Zhang, Yilei Yuan, Hao Zhang, Jin Huang
https://arxiv.org/abs/2510.12087

Can Representation Gaps Be the Key to Enhancing Robustness in Graph-Text Alignment?
Representation learning on text-attributed graphs (TAGs) integrates structural connectivity with rich textual semantics, enabling applications in diverse domains. Current methods largely rely on contrastive learning to maximize cross-modal similarity, assuming tighter coupling between graph and text representations improves transfer performance. However, our empirical analysis reveals that both natural gap expansion and forced gap reduction result in performance degradation by disrupting pre-tr…

Advancing End-to-End Pixel Space Generative Modeling via Self-supervised Pre-training
Jiachen Lei, Keli Liu, Julius Berner, Haiming Yu, Hongkai Zheng, Jiahong Wu, Xiangxiang Chu
https://arxiv.org/abs/2510.12586

Advancing End-to-End Pixel Space Generative Modeling via Self-supervised Pre-training
Pixel-space generative models are often more difficult to train and generally underperform compared to their latent-space counterparts, leaving a persistent performance and efficiency gap. In this paper, we introduce a novel two-stage training framework that closes this gap for pixel-space diffusion and consistency models. In the first stage, we pre-train encoders to capture meaningful semantics from clean images while aligning them with points along the same deterministic sampling trajectory, …

QDER: Query-Specific Document and Entity Representations for Multi-Vector Document Re-Ranking
Shubham Chatterjee, Jeff Dalton
https://arxiv.org/abs/2510.11589 https://

QDER: Query-Specific Document and Entity Representations for Multi-Vector Document Re-Ranking
Neural IR has advanced through two distinct paths: entity-oriented approaches leveraging knowledge graphs and multi-vector models capturing fine-grained semantics. We introduce QDER, a neural re-ranking model that unifies these approaches by integrating knowledge graph semantics into a multi-vector model. QDER's key innovation lies in its modeling of query-document relationships: rather than computing similarity scores on aggregated embeddings, we maintain individual token and entity representa…

Representations
Paul Brunet (UPEC UP12, LACL)
https://arxiv.org/abs/2510.11419 https://arxiv.org/pdf/2510.11419

Representations
The formal analysis of automated systems is an important and growing industry. This activity routinely requires new verification frameworks to be developed to tackle new programming features, or new considerations (bugs of interest). Often, one particular property can prove frustrating to establish: completeness of the logic with respect to the semantics. In this paper, we try and make such developments easier, with a particular attention on completeness. Towards that aim, we propose a formal (…

OBsmith: Testing JavaScript Obfuscator using LLM-powered sketching
Shan Jiang, Chenguang Zhu, Sarfraz Khurshid
https://arxiv.org/abs/2510.10066 https://arx…

OBsmith: Testing JavaScript Obfuscator using LLM-powered sketching
JavaScript obfuscators are widely deployed to protect intellectual property and resist reverse engineering, yet their correctness has been largely overlooked compared to performance and resilience. Existing evaluations typically measure resistance to deobfuscation, leaving the critical question of whether obfuscators preserve program semantics unanswered. Incorrect transformations can silently alter functionality, compromise reliability, and erode security-undermining the very purpose of obfusc…

Data or Language Supervision: What Makes CLIP Better than DINO?
Yiming Liu, Yuhui Zhang, Dhruba Ghosh, Ludwig Schmidt, Serena Yeung-Levy
https://arxiv.org/abs/2510.11835 https:/…

Data or Language Supervision: What Makes CLIP Better than DINO?
CLIP outperforms self-supervised models like DINO as vision encoders for vision-language models (VLMs), but it remains unclear whether this advantage stems from CLIP's language supervision or its much larger training data. To disentangle these factors, we pre-train CLIP and DINO under controlled settings -- using the same architecture, dataset, and training configuration -- achieving similar ImageNet accuracy. Embedding analysis shows that CLIP captures high-level semantics (e.g., object catego…

PRoH: Dynamic Planning and Reasoning over Knowledge Hypergraphs for Retrieval-Augmented Generation
Xiangjun Zai, Xingyu Tan, Xiaoyang Wang, Qing Liu, Xiwei Xu, Wenjie Zhang
https://arxiv.org/abs/2510.12434

PRoH: Dynamic Planning and Reasoning over Knowledge Hypergraphs for Retrieval-Augmented Generation
Knowledge Hypergraphs (KHs) have recently emerged as a knowledge representation for retrieval-augmented generation (RAG), offering a paradigm to model multi-entity relations into a structured form. However, existing KH-based RAG methods suffer from three major limitations: static retrieval planning, non-adaptive retrieval execution, and superficial use of KH structure and semantics, which constrain their ability to perform effective multi-hop question answering. To overcome these limitations, w…

Decoupled Multimodal Fusion for User Interest Modeling in Click-Through Rate Prediction
Alin Fan, Hanqing Li, Sihan Lu, Jingsong Yuan, Jiandong Zhang
https://arxiv.org/abs/2510.11066

Decoupled Multimodal Fusion for User Interest Modeling in Click-Through Rate Prediction
Modern industrial recommendation systems improve recommendation performance by integrating multimodal representations from pre-trained models into ID-based Click-Through Rate (CTR) prediction frameworks. However, existing approaches typically adopt modality-centric modeling strategies that process ID-based and multimodal embeddings independently, failing to capture fine-grained interactions between content semantics and behavioral signals. In this paper, we propose Decoupled Multimodal Fusion (…