Papers

New on arXiv

Sat 23 Aug 2025

153 papers

Real-Time RAG for the Identification of Supply Chain VulnerabilitiesRetrieval-augmented generation → RAG pipeline design and evaluation
AMMKD: Adaptive Multimodal Multi-teacher Distillation for Lightweight Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
Towards Production-Worthy Simulation for Autonomous Cyber OperationsDeep reinforcement learning methods → Adversarial robustness and RL in finance
POT: Inducing Overthinking in LLMs via Black-Box Iterative OptimizationLLM reasoning → Reasoning for agents, planning and code +1
What Matters in Data for DPO?LLM alignment / RLHF / preference optimisation → LLM preference optimization methods
SPORTSQL: An Interactive System for Real-Time Sports Reasoning and VisualizationLLM reasoning → Multimodal reasoning
Mind the Gap: Time-of-Check to Time-of-Use Vulnerabilities in LLM-Enabled AgentsLLM agents and tool use → Agent threats, guardrails and governance
Natural Language Satisfiability: Exploring the Problem Distribution and Evaluating Transformer-based Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
MoE-Beyond: Learning-Based Expert Activation Prediction on Edge DevicesMixture-of-experts → Efficient MoE training and inference systems
PlantExpertVQA: A Visual Question Answering Dataset for Benchmarking Vision-Language Models in Plant ScienceLLM reasoning → Clinical and biomedical applications +1
GRASP: Geospatial pixel Reasoning viA Structured Policy learningLLM reasoning → Spatial and embodied reasoning +1
PowerChain: A Verifiable Agentic AI System for Automating Distribution Grid AnalysesLLM agents and tool use → Financial trading and forecasting agents
Zero-shot Multimodal Document Retrieval via Cross-modal Question GenerationMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
Anemoi: A Semi-Centralized Multi-agent System Based on Agent-to-Agent Communication MCP server from Coral ProtocolLLM agents and tool use → General LLM agent frameworks and benchmarks
GRAID: Synthetic Data Generation with Geometric Constraints and Multi-Agentic Reflection for Harmful Content DetectionLLM agents and tool use → Agent threats, guardrails and governance +2
PVNet: Point-Voxel Interaction LiDAR Scene Upsampling Via Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
Learned Structure in Cartridges: Keys as Shareable Routers in Self-Studied RepresentationsEfficient LLM inference and serving → KV cache optimization
Limitations of refinement methods for weak to strong generalizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
KL-Regularised Q-Learning: A Token-level Action-Value perspective on Online RLHFLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
DeAR: Dual-Stage Document Reranking with Reasoning Agents via LLM DistillationLLM reasoning → Knowledge- and tool-augmented reasoning +1
GRADE: Generating multi-hop QA and fine-gRAined Difficulty matrix for RAG EvaluationRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
Score Matching on Large Geometric Graphs for Cosmology GenerationDiffusion models → Inverse problems and image restoration
Unveiling the Latent Directions of Reflection in Large Language ModelsMechanistic interpretability → Activation steering methods
WebSight: A Vision-First Architecture for Robust Web AgentsLLM agents and tool use → Web, search, and research agents
HiCache: A Plug-in Scaled-Hermite Upgrade for Taylor-Style Cache-then-Forecast Diffusion AccelerationDiffusion models → Diffusion foundations and sampling
ReFactX: Scalable Reasoning with Reliable Facts via Constrained GenerationLLM reasoning → Knowledge- and tool-augmented reasoning
Decoding Alignment: A Critical Survey of LLM Development Initiatives through Value-setting and Data-centric LensLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
Robust Diagram Reasoning: A Framework for Enhancing LVLM Performance on Visually Perturbed Scientific DiagramsLLM reasoning → Multimodal reasoning
Explaining Black-box Language Models with Knowledge Probing Systems: A Post-hoc Explanation PerspectiveLLM reasoning → Reasoning benchmarks and evaluation
LLM-based Human-like Traffic Simulation for Self-driving TestsEnd-to-end autonomous driving → Large language models for driving
RPD-Diff: Region-Adaptive Physics-Guided Diffusion Model for Visibility Enhancement under Dense and Non-Uniform HazeDiffusion models → Inverse problems and image restoration
Disentangling Polysemantic Neurons with a Null-Calibrated Polysemanticity Index and Causal Patch InterventionsMechanistic interpretability → Circuits and mechanistic analysis
Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM ReasoningLLM reasoning → Reinforcement learning for reasoning
Drive As You Like: Multi-Head Diffusion with Reinforcement Learning for Personalized DrivingEnd-to-end autonomous driving → Imitation-learning end-to-end planners +2
LHM-Humanoid: Long-Horizon Human Motion Control for Continuous Object Transport in Cluttered ScenesDeep reinforcement learning methods → RL for robot locomotion and manipulation
Sig-DEG for Distillation: Making Diffusion Models Faster and LighterDiffusion models → Diffusion foundations and sampling
HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio GenerationDiffusion models → Audio, speech and music
Dimensional Collapse in Transformer Attention Outputs: A Challenge for Sparse Dictionary LearningMechanistic interpretability → Sparse autoencoder training and evaluation
Being Kind Isn't Always Being Safe: Diagnosing Affective Hallucination in LLMsLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
Reinforcement-Guided Hyper-Heuristic Hyperparameter Optimization for Fair and Explainable Spiking Neural Network-Based Financial Fraud DetectionDeep reinforcement learning methods → Adversarial robustness and RL in finance
Unbiased Reasoning for Knowledge-Intensive Tasks in Large Language Models via Conditional Front-Door AdjustmentLLM reasoning → Prompting and chain-of-thought reasoning
ObjexMT: Objective Extraction and Metacognitive Calibration for LLM-as-a-Judge under Multi-Turn JailbreaksLLM safety and security → Safety alignment, refusal and guardrails
Dream to Chat: Model-based Reinforcement Learning on Dialogues with User Belief ModelingWorld models → World models for language agents +1
Multimodal LLMs See SentimentMultimodal LLMs / vision-language models → Multimodal emotion understanding
Learning from Diverse Reasoning Paths with Routing and CollaborationLLM reasoning → Prompting and chain-of-thought reasoning
Beyond Emotion Recognition: A Multi-Turn Multimodal Emotion Understanding and Reasoning BenchmarkLLM reasoning → Audio-language model reasoning +1
RADAR: A Reasoning-Guided Attribution Framework for Explainable Visual Data AnalysisLLM reasoning → Multimodal reasoning
NinA: Normalizing Flows in Action. Training VLA Models with Normalizing FlowsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
Deep Learning-based Techniques for Integrated Sensing and Communication Systems: State-of-the-Art, Challenges, and Opportunities
Cross-field SNR Analysis and Tensor Channel Estimation for Multi-UAV Near-field Communications
ARTPS: Depth-Enhanced Hybrid Anomaly Detection and Learnable Curiosity Score for Autonomous Rover Target Prioritization
Spatio-Temporal Pruning for Compressed Spiking Large Language Models
Does Calibration Affect Human Actions?
Evaluating Federated Learning for At-Risk Student Prediction: A Comparative Analysis of Model Complexity and Data Balancing
Automated Landfill Detection Using Deep Learning: A Comparative Study of Lightweight and Custom Architectures with the AerialWaste Dataset
SERES: Semantic-aware neural reconstruction from sparse views
ProtoEHR: Hierarchical Prototype Learning for EHR-based Healthcare Predictions
CoPE: A Lightweight Complex Positional Encoding
Learning Spatio-Temporal Dynamics via Operator-Valued RKHS and Kernel Koopman Methods
SALMAN: Stability Analysis of Language Models Through the Maps Between Graph-based Manifolds
scI2CL: Effectively Integrating Single-cell Multi-omics by Intra- and Inter-omics Contrastive Learning
Error analysis for the deep Kolmogorov method
The Impact of Annotator Personas on LLM Behavior Across the Perspectivism Spectrum
Quantifying Language Disparities in Multilingual Large Language Models
Beyond Play and Pause: Turning GPT-4o Spatial Weakness into a Strength for In-Depth Interactive Video Learning
Towards Safeguarding LLM Fine-tuning APIs against Cipher Attacks
On the sample complexity of semi-supervised multi-objective learning
Integrative Experiments Identify How Punishment Impacts Welfare in Public Goods Games
SACA: Selective Attention-Based Clustering Algorithm
Geolocation-Aware Robust Spoken Language Identification
Stochastic Gradient Descent with Strategic Querying
Frequency Response Identification of Low-Order Systems: Finite-Sample Analysis
Factor Informed Double Deep Learning For Average Treatment Effect Estimation
Rao Differential Privacy
The Power of Framing: How News Headlines Guide Search Behavior
Structural Damage Detection Using AI Super Resolution and Visual Language Model
Reconciling Communication Compression and Byzantine-Robustness in Distributed Learning
CE-RS-SBCIT A Novel Channel Enhanced Hybrid CNN Transformer with Residual, Spatial, and Boundary-Aware Learning for Brain Tumor MRI Analysis
A Straightforward Pipeline for Targeted Entailment and Contradiction Detection
Token Homogenization under Positional Bias
HV Metric For Time-Domain Full Waveform Inversion
SugarcaneShuffleNet: A Very Fast, Lightweight Convolutional Neural Network for Diagnosis of 15 Sugarcane Leaf Diseases
Rethinking How AI Embeds and Adapts to Human Values: Challenges and Opportunities
Two Birds with One Stone: Enhancing Uncertainty Quantification and Interpretability with Graph Functional Neural Process
Convolutional Neural Networks for Accurate Measurement of Train Speed
Enhancing Knowledge Tracing through Leakage-Free and Recency-Aware Embeddings
Neural Stochastic Differential Equations on Compact State Spaces: Theory, Methods, and Application to Suicide Risk Modeling
Solving the Min-Max Multiple Traveling Salesmen Problem via Learning-Based Path Generation and Optimal Splitting
Detecting Multilevel Manipulation from Limit Order Book via Cascaded Contrastive Representation Learning
Learning ON Large Datasets Using Bit-String Trees
PD-Loss: Proxy-Decidability for Efficient Metric Learning
Proximal Vision Transformer: Enhancing Feature Representation through Two-Stage Manifold Geometry
Linguistic Neuron Overlap Patterns to Facilitate Cross-lingual Transfer on Low-resource Languages
CP4SBI: Local Conformal Calibration of Credible Sets in Simulation-Based Inference
Optimizing Neural Networks with Learnable Non-Linear Activation Functions via Lookup-Based FPGA Acceleration
SSG-Dit: A Spatial Signal Guided Framework for Controllable Video Generation
REGEN: Real-Time Photorealism Enhancement in Games via a Dual-Stage Generative Network Framework
TabResFlow: A Normalizing Spline Flow Model for Probabilistic Univariate Tabular Regression
DeltaFlow: An Efficient Multi-frame Scene Flow Estimation Method
Styleclone: Face Stylization with Diffusion Based Data Augmentation

All 153