Tootfinder

A Knowledge Graph Informing Soil Carbon Modeling
Nasim Shirvani-Mahdavi, Devin Wingfield, Juan Guajardo Gutierrez, Mai Tran, Zhengyuan Zhu, Zeyu Zhang, Haiqi Zhang, Abhishek Divakar Goudar, Chengkai Li, Virginia Jin, Timothy Propst, Dan Roberts, Catherine Stewart, Jianzhong Su, Jennifer Woodward-Greene
https://arxiv.org/abs/2508.10965

A Knowledge Graph Informing Soil Carbon Modeling
Soil organic carbon is crucial for climate change mitigation and agricultural sustainability. However, understanding its dynamics requires integrating complex, heterogeneous data from multiple sources. This paper introduces the Soil Organic Carbon Knowledge Graph (SOCKG), a semantic infrastructure designed to transform agricultural research data into a queryable knowledge representation. SOCKG features a robust ontological model of agricultural experimental data, enabling precise mapping of dat…

From Knowledge to Treatment: Large Language Model Assisted Biomedical Concept Representation for Drug Repurposing
Chengrui Xiang, Tengfei Ma, Xiangzheng Fu, Yiping Liu, Bosheng Song, Xiangxiang Zeng
https://arxiv.org/abs/2510.12181

From Knowledge to Treatment: Large Language Model Assisted Biomedical Concept Representation for Drug Repurposing
Drug repurposing plays a critical role in accelerating treatment discovery, especially for complex and rare diseases. Biomedical knowledge graphs (KGs), which encode rich clinical associations, have been widely adopted to support this task. However, existing methods largely overlook common-sense biomedical concept knowledge in real-world labs, such as mechanistic priors indicating that certain drugs are fundamentally incompatible with specific treatments. To address this gap, we propose LLaDR, …

SPARK: Adaptive Low-Rank Knowledge Graph Modeling in Hybrid Geometric Spaces for Recommendation
Binhao Wang, Yutian Xiao, Maolin Wang, Zhiqi Li, Tianshuo Wei, Ruocheng Guo, Xiangyu Zhao
https://arxiv.org/abs/2509.11094

SPARK: Adaptive Low-Rank Knowledge Graph Modeling in Hybrid Geometric Spaces for Recommendation
Knowledge Graphs (KGs) enhance recommender systems but face challenges from inherent noise, sparsity, and Euclidean geometry's inadequacy for complex relational structures, critically impairing representation learning, especially for long-tail entities. Existing methods also often lack adaptive multi-source signal fusion tailored to item popularity. This paper introduces SPARK, a novel multi-stage framework systematically tackling these issues. SPARK first employs Tucker low-rank decomposition …

Query-Specific GNN: A Comprehensive Graph Representation Learning Method for Retrieval Augmented Generation
Yuchen Yan, Zhihua Liu, Hao Wang, Weiming Li, Xiaoshuai Hao
https://arxiv.org/abs/2510.11541 …

Query-Specific GNN: A Comprehensive Graph Representation Learning Method for Retrieval Augmented Generation
Retrieval-augmented generation (RAG) has demonstrated its ability to enhance Large Language Models (LLMs) by integrating external knowledge sources. However, multi-hop questions, which require the identification of multiple knowledge targets to form a synthesized answer, raise new challenges for RAG systems. Under the multi-hop settings, existing methods often struggle to fully understand the questions with complex semantic structures and are susceptible to irrelevant noise during the retrieval…

E2-BKI: Evidential Ellipsoidal Bayesian Kernel Inference for Uncertainty-aware Gaussian Semantic Mapping
Junyoung Kim, Minsik Jeon, Jihong Min, Kiho Kwak, Junwon Seo
https://arxiv.org/abs/2509.11964

E2-BKI: Evidential Ellipsoidal Bayesian Kernel Inference for Uncertainty-aware Gaussian Semantic Mapping
Semantic mapping aims to construct a 3D semantic representation of the environment, providing essential knowledge for robots operating in complex outdoor settings. While Bayesian Kernel Inference (BKI) addresses discontinuities of map inference from sparse sensor data, existing semantic mapping methods suffer from various sources of uncertainties in challenging outdoor environments. To address these issues, we propose an uncertainty-aware semantic mapping framework that handles multiple sources…

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…

BioMetaphor: AI-Generated Biodata Representations for Virtual Co-Present Events
Lin Lin, Ming Wu, Anyu Ren, Zhanwei Wu, Daojun Gong, Ruowei Xiao
https://arxiv.org/abs/2509.11600

BioMetaphor: AI-Generated Biodata Representations for Virtual Co-Present Events
In virtual or hybrid co-present events, biodata is emerging as a new paradigm of social cues. While it is able to reveal individuals' inner states, the technology-mediated representation of biodata in social contexts remains underexplored. This study aims to uncover human cognitive preferences and patterns for biodata expression and leverage this knowledge to guide generative AI (GenAI) in creating biodata representations for co-present experiences, aligning with the broader concept of Human-in…

Representation-Aware Distributionally Robust Optimization: A Knowledge Transfer Framework
Zitao Wang, Nian Si, Molei Liu
https://arxiv.org/abs/2509.09371 https://

Representation-Aware Distributionally Robust Optimization: A Knowledge Transfer Framework
We propose REpresentation-Aware Distributionally Robust Estimation (READ), a novel framework for Wasserstein distributionally robust learning that accounts for predictive representations when guarding against distributional shifts. Unlike classical approaches that treat all feature perturbations equally, READ embeds a multidimensional alignment parameter into the transport cost, allowing the model to differentially discourage perturbations along directions associated with informative representa…

Representation-Based Exploration for Language Models: From Test-Time to Post-Training
Jens Tuyls, Dylan J. Foster, Akshay Krishnamurthy, Jordan T. Ash
https://arxiv.org/abs/2510.11686

Representation-Based Exploration for Language Models: From Test-Time to Post-Training
Reinforcement learning (RL) promises to expand the capabilities of language models, but it is unclear if current RL techniques promote the discovery of novel behaviors, or simply sharpen those already present in the base model. In this paper, we investigate the value of deliberate exploration -- explicitly incentivizing the model to discover novel and diverse behaviors -- and aim to understand how the knowledge in pre-trained models can guide this search. Our main finding is that exploration wi…

Eat your own KR: a KR-based approach to index Semantic Web Endpoints and Knowledge Graphs
Pierre Maillot (WIMMICS), Catherine Faron (UniCA, I3S, WIMMICS), Fabien Gandon (WIMMICS), Franck Michel (Laboratoire I3S - SPARKS, WIMMICS), Pierre Monnin (WIMMICS)
https://arxiv.org/abs/2508.08713

Eat your own KR: a KR-based approach to index Semantic Web Endpoints and Knowledge Graphs
Over the last decade, knowledge graphs have multiplied, grown, and evolved on the World Wide Web, and the advent of new standards, vocabularies, and application domains has accelerated this trend. IndeGx is a framework leveraging an extensible base of rules to index the content of KGs and the capacities of their SPARQL endpoints. In this article, we show how knowledge representation (KR) and reasoning methods and techniques can be used in a reflexive manner to index and characterize existing kn…

Steering Language Models in Multi-Token Generation: A Case Study on Tense and Aspect
Alina Klerings, Jannik Brinkmann, Daniel Ruffinelli, Simone Ponzetto
https://arxiv.org/abs/2509.12065

Steering Language Models in Multi-Token Generation: A Case Study on Tense and Aspect
Large language models (LLMs) are able to generate grammatically well-formed text, but how do they encode their syntactic knowledge internally? While prior work has focused largely on binary grammatical contrasts, in this work, we study the representation and control of two multidimensional hierarchical grammar phenomena - verb tense and aspect - and for each, identify distinct, orthogonal directions in residual space using linear discriminant analysis. Next, we demonstrate causal control over b…

Multi-Ontology Integration with Dual-Axis Propagation for Medical Concept Representation
Mohsen Nayebi Kerdabadi, Arya Hadizadeh Moghaddam, Dongjie Wang, Zijun Yao
https://arxiv.org/abs/2508.21320

Multi-Ontology Integration with Dual-Axis Propagation for Medical Concept Representation
Medical ontology graphs map external knowledge to medical codes in electronic health records via structured relationships. By leveraging domain-approved connections (e.g., parent-child), predictive models can generate richer medical concept representations by incorporating contextual information from related concepts. However, existing literature primarily focuses on incorporating domain knowledge from a single ontology system, or from multiple ontology systems (e.g., diseases, drugs, and proce…

The KG-ER Conceptual Schema Language
Enrico Franconi, Beno\^it Groz, Jan Hidders, Nina Pardal, S{\l}awek Staworko, Jan Van den Bussche, Piotr Wieczorek
https://arxiv.org/abs/2508.02548

The KG-ER Conceptual Schema Language
We propose KG-ER, a conceptual schema language for knowledge graphs that describes the structure of knowledge graphs independently of their representation (relational databases, property graphs, RDF) while helping to capture the semantics of the information stored in a knowledge graph.

DRKF: Decoupled Representations with Knowledge Fusion for Multimodal Emotion Recognition
Peiyuan Jiang (School of Computer Science,Engineering, University of Electronic Science,Technology of China), Yao Liu (School of Information,Software Engineering, University of Electronic Science,Technology of China), Qiao Liu (School of Computer Science,Engineering, University of Electronic Science,Technology of China), Zongshun Zhang (School of Computer Science,Engineering, University of Electron…

DRKF: Decoupled Representations with Knowledge Fusion for Multimodal Emotion Recognition
Multimodal emotion recognition (MER) aims to identify emotional states by integrating and analyzing information from multiple modalities. However, inherent modality heterogeneity and inconsistencies in emotional cues remain key challenges that hinder performance. To address these issues, we propose a Decoupled Representations with Knowledge Fusion (DRKF) method for MER. DRKF consists of two main modules: an Optimized Representation Learning (ORL) Module and a Knowledge Fusion (KF) Module. ORL e…

Putting Perspective into OWL [sic]: Complexity-Neutral Standpoint Reasoning for Ontology Languages via Monodic S5 over Counting Two-Variable First-Order Logic (Extended Version with Appendix)
Luc\'ia G\'omez \'Alvarez, Sebastian Rudolph
https://arxiv.org/abs/2508.00653

Putting Perspective into OWL [sic]: Complexity-Neutral Standpoint Reasoning for Ontology Languages via Monodic S5 over Counting Two-Variable First-Order Logic (Extended Version with Appendix)
Standpoint extensions of knowledge representation formalisms have been recently introduced as a means to incorporate multi-perspective modelling and reasoning through modal operators that attribute pieces of knowledge to specific entities or agents. In these extensions, the integration between conceptual modelling and perspective annotations can vary in strength, with monodic standpoint extensions offering a well-balanced approach. They allow for advanced modelling features, such as the express…

MedCAL-Bench: A Comprehensive Benchmark on Cold-Start Active Learning with Foundation Models for Medical Image Analysis
Ning Zhu, Xiaochuan Ma, Shaoting Zhang, Guotai Wang
https://arxiv.org/abs/2508.03441

MedCAL-Bench: A Comprehensive Benchmark on Cold-Start Active Learning with Foundation Models for Medical Image Analysis
Cold-Start Active Learning (CSAL) aims to select informative samples for annotation without prior knowledge, which is important for improving annotation efficiency and model performance under a limited annotation budget in medical image analysis. Most existing CSAL methods rely on Self-Supervised Learning (SSL) on the target dataset for feature extraction, which is inefficient and limited by insufficient feature representation. Recently, pre-trained Foundation Models (FMs) have shown powerful f…

VISaGE: Understanding Visual Generics and Exceptions
Stella Frank, Emily Allaway
https://arxiv.org/abs/2510.12548 https://arxiv.org/pdf/2510.12548

VISaGE: Understanding Visual Generics and Exceptions
While Vision Language Models (VLMs) learn conceptual representations, in the form of generalized knowledge, during training, they are typically used to analyze individual instances. When evaluation instances are atypical, this paradigm results in tension between two priors in the model. The first is a pragmatic prior that the textual and visual input are both relevant, arising from VLM finetuning on congruent inputs; the second is a semantic prior that the conceptual representation is generally…

Wave-Based Semantic Memory with Resonance-Based Retrieval: A Phase-Aware Alternative to Vector Embedding Stores
Aleksandr Listopad
https://arxiv.org/abs/2509.09691 https://

Wave-Based Semantic Memory with Resonance-Based Retrieval: A Phase-Aware Alternative to Vector Embedding Stores
Conventional vector-based memory systems rely on cosine or inner product similarity within real-valued embedding spaces. While computationally efficient, such approaches are inherently phase-insensitive and limited in their ability to capture resonance phenomena crucial for meaning representation. We propose Wave-Based Semantic Memory, a novel framework that models knowledge as wave patterns $ψ(x) = A(x) e^{iϕ(x)}$ and retrieves it through resonance-based interference. This approach preserves…

KEEP: Integrating Medical Ontologies with Clinical Data for Robust Code Embeddings
Ahmed Elhussein, Paul Meddeb, Abigail Newbury, Jeanne Mirone, Martin Stoll, Gamze Gursoy
https://arxiv.org/abs/2510.05049

KEEP: Integrating Medical Ontologies with Clinical Data for Robust Code Embeddings
Machine learning in healthcare requires effective representation of structured medical codes, but current methods face a trade off: knowledge graph based approaches capture formal relationships but miss real world patterns, while data driven methods learn empirical associations but often overlook structured knowledge in medical terminologies. We present KEEP (Knowledge preserving and Empirically refined Embedding Process), an efficient framework that bridges this gap by combining knowledge grap…

Information Ecosystem Reengineering via Public Sector Knowledge Representation
Mayukh Bagchi
https://arxiv.org/abs/2508.15916 https://arxiv.org/pdf/2508.15…

Information Ecosystem Reengineering via Public Sector Knowledge Representation
Information Ecosystem Reengineering (IER) -- the technological reconditioning of information sources, services, and systems within a complex information ecosystem -- is a foundational challenge in the digital transformation of public sector services and smart governance platforms. From a semantic knowledge management perspective, IER becomes especially entangled due to the potentially infinite number of possibilities in its conceptualization, namely, as a result of manifoldness in the multi-lev…

Replaced article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[1/5]:
- MLRIP: Pre-training a military language representation model with informative factual knowledge a...
Hui Li, Xuekang Yang

LLM-based Triplet Extraction for Automated Ontology Generation in Software Engineering Standards
Songhui Yue
https://arxiv.org/abs/2509.00140 https://arxiv…

LLM-based Triplet Extraction for Automated Ontology Generation in Software Engineering Standards
Ontologies have supported knowledge representation and whitebox reasoning for decades; thus, the automated ontology generation (AOG) plays a crucial role in scaling their use. Software engineering standards (SES) consist of long, unstructured text (with high noise) and paragraphs with domain-specific terms. In this setting, relation triple extraction (RTE), together with term extraction, constitutes the first stage toward AOG. This work proposes an open-source large language model (LLM)-assiste…

MolGA: Molecular Graph Adaptation with Pre-trained 2D Graph Encoder
Xingtong Yu, Chang Zhou, Xinming Zhang, Yuan Fang
https://arxiv.org/abs/2510.07289 https://

MolGA: Molecular Graph Adaptation with Pre-trained 2D Graph Encoder
Molecular graph representation learning is widely used in chemical and biomedical research. While pre-trained 2D graph encoders have demonstrated strong performance, they overlook the rich molecular domain knowledge associated with submolecular instances (atoms and bonds). While molecular pre-training approaches incorporate such knowledge into their pre-training objectives, they typically employ designs tailored to a specific type of knowledge, lacking the flexibility to integrate diverse knowl…

SONAR: Self-Distilled Continual Pre-training for Domain Adaptive Audio Representation
Yizhou Zhang, Yuan Gao, Wangjin Zhou, Zicheng Yuan, Keisuke Imoto, Tatsuya Kawahara
https://arxiv.org/abs/2509.15703

SONAR: Self-Distilled Continual Pre-training for Domain Adaptive Audio Representation
Self-supervised learning (SSL) on large-scale datasets like AudioSet has become the dominant paradigm for audio representation learning. While the continuous influx of new, unlabeled audio presents an opportunity to enrich these static representations, a naive approach is to retrain the model from scratch using all available data. However, this method is computationally prohibitive and discards the valuable knowledge embedded in the previously trained model weights. To address this inefficiency…

Generative Large Language Models for Knowledge Representation: A Systematic Review of Concept Map Generation
Xiaoming Zhai
https://arxiv.org/abs/2509.14554 https://

Generative Large Language Models for Knowledge Representation: A Systematic Review of Concept Map Generation
The rise of generative large language models (LLMs) has opened new opportunities for automating knowledge representation through concept maps, a long-standing pedagogical tool valued for fostering meaningful learning and higher-order thinking. Traditional construction of concept maps is labor-intensive, requiring significant expertise and time, limiting their scalability in education. This review systematically synthesizes the emerging body of research on LLM-enabled concept map generation, foc…

“But the insight was never lived. It was stored”
“I stopped wondering and started processing”
“Merlin Donald … argues that human intelligence emerged not from static memory storage but from external symbolic representation: tools like language, gesture, and writing that allowed us to rehearse, share, and restructure thought. Culture became a collective memory system - not to archive knowledge, but to keep it alive, replayed, and reworked”

VER: Vision Expert Transformer for Robot Learning via Foundation Distillation and Dynamic Routing
Yixiao Wang, Mingxiao Huo, Zhixuan Liang, Yushi Du, Lingfeng Sun, Haotian Lin, Jinghuan Shang, Chensheng Peng, Mohit Bansal, Mingyu Ding, Masayoshi Tomizuka
https://arxiv.org/abs/2510.05213

VER: Vision Expert Transformer for Robot Learning via Foundation Distillation and Dynamic Routing
Pretrained vision foundation models (VFMs) advance robotic learning via rich visual representations, yet individual VFMs typically excel only in specific domains, limiting generality across tasks. Distilling multiple VFMs into a unified representation for policy can mitigate this limitation but often yields inflexible task-specific feature selection and requires costly full re-training to incorporate robot-domain knowledge. We propose VER, a Vision Expert transformer for Robot learning. During …

Relational Database Distillation: From Structured Tables to Condensed Graph Data
Xinyi Gao, Jingxi Zhang, Lijian Chen, Tong Chen, Lizhen Cui, Hongzhi Yin
https://arxiv.org/abs/2510.06980

Relational Database Distillation: From Structured Tables to Condensed Graph Data
Relational databases (RDBs) underpin the majority of global data management systems, where information is structured into multiple interdependent tables. To effectively use the knowledge within RDBs for predictive tasks, recent advances leverage graph representation learning to capture complex inter-table relations as multi-hop dependencies. Despite achieving state-of-the-art performance, these methods remain hindered by the prohibitive storage overhead and excessive training time, due to the m…

Hierarchical knowledge guided fault intensity diagnosis of complex industrial systems
Yu Sha, Shuiping Gou, Bo Liu, Johannes Faber, Ningtao Liu, Stefan Schramm, Horst Stoecker, Thomas Steckenreiter, Domagoj Vnucec, Nadine Wetzstein, Andreas Widl, Kai Zhou
https://arxiv.org/abs/2508.12375

Hierarchical knowledge guided fault intensity diagnosis of complex industrial systems
Fault intensity diagnosis (FID) plays a pivotal role in monitoring and maintaining mechanical devices within complex industrial systems. As current FID methods are based on chain of thought without considering dependencies among target classes. To capture and explore dependencies, we propose a hierarchical knowledge guided fault intensity diagnosis framework (HKG) inspired by the tree of thought, which is amenable to any representation learning methods. The HKG uses graph convolutional networks…

KAME: Tandem Architecture for Enhancing Knowledge in Real-Time Speech-to-Speech Conversational AI
So Kuroki, Yotaro Kubo, Takuya Akiba, Yujin Tang
https://arxiv.org/abs/2510.02327

KAME: Tandem Architecture for Enhancing Knowledge in Real-Time Speech-to-Speech Conversational AI
Real-time speech-to-speech (S2S) models excel at generating natural, low-latency conversational responses but often lack deep knowledge and semantic understanding. Conversely, cascaded systems combining automatic speech recognition, a text-based Large Language Model (LLM), and text-to-speech synthesis offer superior knowledge representation at the cost of high latency, which disrupts the flow of natural interaction. This paper introduces a novel hybrid architecture that bridges the gap between …

Food Data in the Semantic Web: A Review of Nutritional Resources, Knowledge Graphs, and Emerging Applications
Darko Sasanski, Riste Stojanov
https://arxiv.org/abs/2509.00986 htt…

Food Data in the Semantic Web: A Review of Nutritional Resources, Knowledge Graphs, and Emerging Applications
This comprehensive review explores food data in the Semantic Web, highlighting key nutritional resources, knowledge graphs, and emerging applications in the food domain. It examines prominent food data resources such as USDA, FoodOn, FooDB, and Recipe1M+, emphasizing their contributions to nutritional data representation. Special focus is given to food entity linking and recognition techniques, which enable integration of heterogeneous food data sources into cohesive semantic resources. The rev…

Representation Learning of Auxiliary Concepts for Improved Student Modeling and Exercise Recommendation
Yahya Badran, Christine Preisach
https://arxiv.org/abs/2508.16269 https:/…

Representation Learning of Auxiliary Concepts for Improved Student Modeling and Exercise Recommendation
Personalized recommendation is a key feature of intelligent tutoring systems, typically relying on accurate models of student knowledge. Knowledge Tracing (KT) models enable this by estimating a student's mastery based on their historical interactions. Many KT models rely on human-annotated knowledge concepts (KCs), which tag each exercise with one or more skills or concepts believed to be necessary for solving it. However, these KCs can be incomplete, error-prone, or overly general. In this …

Learning from nature: insights into GraphDOP's representations of the Earth System
Peter Lean, Mihai Alexe, Eulalie Boucher, Ewan Pinnington, Simon Lang, Patrick Laloyaux, Niels Bormann, Anthony McNally
https://arxiv.org/abs/2508.18018

Learning from nature: insights into GraphDOP's representations of the Earth System
Through a series of experiments, we provide evidence that the GraphDOP model - trained solely on meteorological observations, using no prior knowledge - develops internal representations of the Earth System state, structure and dynamics as well as the characteristics of different observing systems. Firstly, we demonstrate that the network constructs a unified latent representation of the Earth System state which is common across different observation types. For example, cloud structures maintai…

EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs
Yuhao Zhang, Yuhao Du, Zhanchen Dai, Xiangnan Ma, Kaiqi Kou, Benyou Wang, Haizhou Li
https://arxiv.org/abs/2509.09174

EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs
Speech-to-speech large language models (SLLMs) are attracting increasing attention. Derived from text-based large language models (LLMs), SLLMs often exhibit degradation in knowledge and reasoning capabilities. We hypothesize that this limitation arises because current training paradigms for SLLMs fail to bridge the acoustic-semantic gap in the feature representation space. To address this issue, we propose EchoX, which leverages semantic representations and dynamically generates speech trainin…

RACap: Relation-Aware Prompting for Lightweight Retrieval-Augmented Image Captioning
Xiaosheng Long, Hanyu Wang, Zhentao Song, Kun Luo, Hongde Liu
https://arxiv.org/abs/2509.15883

RACap: Relation-Aware Prompting for Lightweight Retrieval-Augmented Image Captioning
Recent retrieval-augmented image captioning methods incorporate external knowledge to compensate for the limitations in comprehending complex scenes. However, current approaches face challenges in relation modeling: (1) the representation of semantic prompts is too coarse-grained to capture fine-grained relationships; (2) these methods lack explicit modeling of image objects and their semantic relationships. To address these limitations, we propose RACap, a relation-aware retrieval-augmented mo…

Choice Outweighs Effort: Facilitating Complementary Knowledge Fusion in Federated Learning via Re-calibration and Merit-discrimination
Ming Yang, Dongrun Li, Xin Wang, Xiaoyang Yu, Xiaoming Wu, Shibo He
https://arxiv.org/abs/2508.17954

Choice Outweighs Effort: Facilitating Complementary Knowledge Fusion in Federated Learning via Re-calibration and Merit-discrimination
Cross-client data heterogeneity in federated learning induces biases that impede unbiased consensus condensation and the complementary fusion of generalization- and personalization-oriented knowledge. While existing approaches mitigate heterogeneity through model decoupling and representation center loss, they often rely on static and restricted metrics to evaluate local knowledge and adopt global alignment too rigidly, leading to consensus distortion and diminished model adaptability. To addre…

Implicitly and Differentiably Representing Protein Surfaces and Interfaces
Cory B. Scott, Charlie Rothschild, Benjamin Nye
https://arxiv.org/abs/2508.11641 https://

Implicitly and Differentiably Representing Protein Surfaces and Interfaces
We introduce a pipeline for representing a protein, or protein complex, as the union of signed distance functions (SDFs) by representing each atom as a sphere with the appropriate radius. While this idea has been used previously as a way to render images of proteins, it has not, to our knowledge, been widely adopted in a machine learning setting. Mirroring recent successful work applying SDFs to represent 3D geometry, we present a proof of concept that this representation of proteins could be u…

Finite Axiomatizability by Disjunctive Existential Rules
Marco Calautti, Marco Console, Andreas Pieris
https://arxiv.org/abs/2508.11946 https://arxiv.org/p…

Finite Axiomatizability by Disjunctive Existential Rules
Rule-based languages lie at the core of several areas of central importance to databases and artificial intelligence such as deductive databases and knowledge representation and reasoning. Disjunctive existential rules (a.k.a. disjunctive tuple-generating dependencies in the database literature) form such a prominent rule-based language. The goal of this work is to pinpoint the expressive power of disjunctive existential rules in terms of insightful model-theoretic properties. More precisely, g…

Embedding Domain Knowledge for Large Language Models via Reinforcement Learning from Augmented Generation
Chaojun Nie, Jun Zhou, Guanxiang Wang, Shisong Wud, Zichen Wang
https://arxiv.org/abs/2509.20162

Embedding Domain Knowledge for Large Language Models via Reinforcement Learning from Augmented Generation
Large language models (LLMs) often exhibit limited performance on domain-specific tasks due to the natural disproportionate representation of specialized information in their training data and the static nature of these datasets. Knowledge scarcity and temporal lag create knowledge gaps for domain applications. While post-training on domain datasets can embed knowledge into models, existing approaches have some limitations. Continual Pre-Training (CPT) treats all tokens in domain documents with…

T-ILR: a Neurosymbolic Integration for LTLf
Riccardo Andreoni, Andrei Buliga, Alessandro Daniele, Chiara Ghidini, Marco Montali, Massimiliano Ronzani
https://arxiv.org/abs/2508.15943

T-ILR: a Neurosymbolic Integration for LTLf
State-of-the-art approaches for integrating symbolic knowledge with deep learning architectures have demonstrated promising results in static domains. However, methods to handle temporal logic specifications remain underexplored. The only existing approach relies on an explicit representation of a finite-state automaton corresponding to the temporal specification. Instead, we aim at proposing a neurosymbolic framework designed to incorporate temporal logic specifications, expressed in Linear Te…

HELIOS: Hierarchical Exploration for Language-grounded Interaction in Open Scenes
Katrina Ashton, Chahyon Ku, Shrey Shah, Wen Jiang, Kostas Daniilidis, Bernadette Bucher
https://arxiv.org/abs/2509.22498

HELIOS: Hierarchical Exploration for Language-grounded Interaction in Open Scenes
Language-specified mobile manipulation tasks in novel environments simultaneously face challenges interacting with a scene which is only partially observed, grounding semantic information from language instructions to the partially observed scene, and actively updating knowledge of the scene with new observations. To address these challenges, we propose HELIOS, a hierarchical scene representation and associated search objective to perform language specified pick and place mobile manipulation ta…

NIRS: An Ontology for Non-Invasive Respiratory Support in Acute Care
Md Fantacher Islam, Jarrod Mosier, Vignesh Subbian
https://arxiv.org/abs/2507.19992 https://

NIRS: An Ontology for Non-Invasive Respiratory Support in Acute Care
Objective: Develop a Non Invasive Respiratory Support (NIRS) ontology to support knowledge representation in acute care settings. Materials and Methods: We developed the NIRS ontology using Web Ontology Language (OWL) semantics and Protege to organize clinical concepts and relationships. To enable rule-based clinical reasoning beyond hierarchical structures, we added Semantic Web Rule Language (SWRL) rules. We evaluated logical reasoning by adding 17 hypothetical patient clinical scenarios. W…

T-ILR: a Neurosymbolic Integration for LTLf
Riccardo Andreoni, Andrei Buliga, Alessandro Daniele, Chiara Ghidini, Marco Montali, Massimiliano Ronzani
https://arxiv.org/abs/2508.15943

T-ILR: a Neurosymbolic Integration for LTLf
State-of-the-art approaches for integrating symbolic knowledge with deep learning architectures have demonstrated promising results in static domains. However, methods to handle temporal logic specifications remain underexplored. The only existing approach relies on an explicit representation of a finite-state automaton corresponding to the temporal specification. Instead, we aim at proposing a neurosymbolic framework designed to incorporate temporal logic specifications, expressed in Linear Te…

S2Sent: Nested Selectivity Aware Sentence Representation Learning
Jianxiang Zang, Nijia Mo, Yonda Wei, Meiling Ning, Hui Liu
https://arxiv.org/abs/2508.18164 https://

S2Sent: Nested Selectivity Aware Sentence Representation Learning
The combination of Transformer-based encoders with contrastive learning represents the current mainstream paradigm for sentence representation learning. This paradigm is typically based on the hidden states of the last Transformer block of the encoder. However, within Transformer-based encoders, different blocks exhibit varying degrees of semantic perception ability. From the perspective of interpretability, the semantic perception potential of knowledge neurons is modulated by stimuli, thus ra…

ViRN: Variational Inference and Distribution Trilateration for Long-Tailed Continual Representation Learning
Hao Dai, Chong Tang, Jagmohan Chauhan
https://arxiv.org/abs/2507.17368

ViRN: Variational Inference and Distribution Trilateration for Long-Tailed Continual Representation Learning
Continual learning (CL) with long-tailed data distributions remains a critical challenge for real-world AI systems, where models must sequentially adapt to new classes while retaining knowledge of old ones, despite severe class imbalance. Existing methods struggle to balance stability and plasticity, often collapsing under extreme sample scarcity. To address this, we propose ViRN, a novel CL framework that integrates variational inference (VI) with distributional trilateration for robust long-t…

PGMEL: Policy Gradient-based Generative Adversarial Network for Multimodal Entity Linking
KM Pooja, Cheng Long, Aixin Sun
https://arxiv.org/abs/2510.02726 https://

PGMEL: Policy Gradient-based Generative Adversarial Network for Multimodal Entity Linking
The task of entity linking, which involves associating mentions with their respective entities in a knowledge graph, has received significant attention due to its numerous potential applications. Recently, various multimodal entity linking (MEL) techniques have been proposed, targeted to learn comprehensive embeddings by leveraging both text and vision modalities. The selection of high-quality negative samples can potentially play a crucial role in metric/representation learning. However, to th…

Investigating Multi-layer Representations for Dense Passage Retrieval
Zhongbin Xie, Thomas Lukasiewicz
https://arxiv.org/abs/2509.23861 https://arxiv.org/p…

Investigating Multi-layer Representations for Dense Passage Retrieval
Dense retrieval models usually adopt vectors from the last hidden layer of the document encoder to represent a document, which is in contrast to the fact that representations in different layers of a pre-trained language model usually contain different kinds of linguistic knowledge, and behave differently during fine-tuning. Therefore, we propose to investigate utilizing representations from multiple encoder layers to make up the representation of a document, which we denote Multi-layer Represe…

Reliable Unlearning Harmful Information in LLMs with Metamorphosis Representation Projection
Chengcan Wu, Zeming Wei, Huanran Chen, Yinpeng Dong, Meng Sun
https://arxiv.org/abs/2508.15449

Reliable Unlearning Harmful Information in LLMs with Metamorphosis Representation Projection
While Large Language Models (LLMs) have demonstrated impressive performance in various domains and tasks, concerns about their safety are becoming increasingly severe. In particular, since models may store unsafe knowledge internally, machine unlearning has emerged as a representative paradigm to ensure model safety. Existing approaches employ various training techniques, such as gradient ascent and negative preference optimization, in attempts to eliminate the influence of undesired data on ta…

Sparse-Autoencoder-Guided Internal Representation Unlearning for Large Language Models
Tomoya Yamashita, Akira Ito, Yuuki Yamanaka, Masanori Yamada, Takayuki Miura, Toshiki Shibahara
https://arxiv.org/abs/2509.15631

Sparse-Autoencoder-Guided Internal Representation Unlearning for Large Language Models
As large language models (LLMs) are increasingly deployed across various applications, privacy and copyright concerns have heightened the need for more effective LLM unlearning techniques. Many existing unlearning methods aim to suppress undesirable outputs through additional training (e.g., gradient ascent), which reduces the probability of generating such outputs. While such suppression-based approaches can control model outputs, they may not eliminate the underlying knowledge embedded in the…

Enhancing Transferability and Consistency in Cross-Domain Recommendations via Supervised Disentanglement
Yuhan Wang, Qing Xie, Zhifeng Bao, Mengzi Tang, Lin Li, Yongjian Liu
https://arxiv.org/abs/2507.17112

Enhancing Transferability and Consistency in Cross-Domain Recommendations via Supervised Disentanglement
Cross-domain recommendation (CDR) aims to alleviate the data sparsity by transferring knowledge across domains. Disentangled representation learning provides an effective solution to model complex user preferences by separating intra-domain features (domain-shared and domain-specific features), thereby enhancing robustness and interpretability. However, disentanglement-based CDR methods employing generative modeling or GNNs with contrastive objectives face two key challenges: (i) pre-separation…

CreAgentive: An Agent Workflow Driven Multi-Category Creative Generation Engine
Yuyang Cheng, Linyue Cai, Changwei Peng, Yumiao Xu, Rongfang Bie, Yong Zhao
https://arxiv.org/abs/2509.26461

CreAgentive: An Agent Workflow Driven Multi-Category Creative Generation Engine
We present CreAgentive, an agent workflow driven multi-category creative generation engine that addresses four key limitations of contemporary large language models in writing stories, drama and other categories of creatives: restricted genre diversity, insufficient output length, weak narrative coherence, and inability to enforce complex structural constructs. At its core, CreAgentive employs a Story Prototype, which is a genre-agnostic, knowledge graph-based narrative representation that deco…

Advancing Natural Language Formalization to First Order Logic with Fine-tuned LLMs
Felix Vossel, Till Mossakowski, Bj\"orn Gehrke
https://arxiv.org/abs/2509.22338 https://

Advancing Natural Language Formalization to First Order Logic with Fine-tuned LLMs
Automating the translation of natural language to first-order logic (FOL) is crucial for knowledge representation and formal methods, yet remains challenging. We present a systematic evaluation of fine-tuned LLMs for this task, comparing architectures (encoder-decoder vs. decoder-only) and training strategies. Using the MALLS and Willow datasets, we explore techniques like vocabulary extension, predicate conditioning, and multilingual training, introducing metrics for exact match, logical equiv…

LLM-Enhanced Linear Autoencoders for Recommendation
Jaewan Moon, Seongmin Park, Jongwuk Lee
https://arxiv.org/abs/2508.13500 https://arxiv.org/pdf/2508.135…

LLM-Enhanced Linear Autoencoders for Recommendation
Large language models (LLMs) have been widely adopted to enrich the semantic representation of textual item information in recommender systems. However, existing linear autoencoders (LAEs) that incorporate textual information rely on sparse word co-occurrence patterns, limiting their ability to capture rich textual semantics. To address this, we propose L3AE, the first integration of LLMs into the LAE framework. L3AE effectively integrates the heterogeneous knowledge of textual semantics and us…

Disentangling concept semantics via multilingual averaging in Sparse Autoencoders
Cliff O'Reilly, Ernesto Jimenez-Ruiz, Tillman Weyde
https://arxiv.org/abs/2508.14275 https:…

Disentangling concept semantics via multilingual averaging in Sparse Autoencoders
Connecting LLMs with formal knowledge representation and reasoning is a promising approach to address their shortcomings. Embeddings and sparse autoencoders are widely used to represent textual content, but the semantics are entangled with syntactic and language-specific information. We propose a method that isolates concept semantics in Large Langue Models by averaging concept activations derived via Sparse Autoencoders. We create English text representations from OWL ontology classes, transla…

Whispering Context: Distilling Syntax and Semantics for Long Speech Transcripts
Duygu Altinok
https://arxiv.org/abs/2508.13376 https://arxiv.org/pdf/2508.1…

Whispering Context: Distilling Syntax and Semantics for Long Speech Transcripts
ASR systems often struggle with maintaining syntactic and semantic accuracy in long audio transcripts, impacting tasks like Named Entity Recognition (NER), capitalization, and punctuation. We propose a novel approach that enhances ASR by distilling contextual knowledge from LLaMA models into Whisper. Our method uses two strategies: (1) token level distillation with optimal transport to align dimensions and sequence lengths, and (2) representation loss minimization between sentence embeddings of…