Papers

New on arXiv

Tue 22 Jul 2025

337 papers

Prototype-Guided Pseudo-Labeling with Neighborhood-Aware Consistency for Unsupervised AdaptationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
CIMR: Contextualized Iterative Multimodal Reasoning for Robust Instruction Following in LVLMsLLM reasoning → Multimodal reasoning +1
TRIDENT: Benchmarking LLM Safety in Finance, Medicine, and LawLLM safety and security → Safety alignment, refusal and guardrails
Can You Trust an LLM with Your Life-Changing Decision? An Investigation into AI High-Stakes ResponsesMechanistic interpretability → Probing deception, bias and beliefs
Comparing Behavioural Cloning and Reinforcement Learning for Spacecraft Guidance and Control NetworksOffline RL and imitation learning from data → Imitation learning methods +1
Diffusion Models for Solving Inverse Problems via Posterior Sampling with Piecewise GuidanceDiffusion models → Inverse problems and image restoration
Livatar-1: Real-Time Talking Heads Generation with Tailored Flow MatchingDiffusion models → Audio, speech and music
VL-CLIP: Enhancing Multimodal Recommendations via Visual Grounding and LLM-Augmented CLIP EmbeddingsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
LoRA is All You Need for Safety Alignment of Reasoning LLMsLLM reasoning → Reasoning for agents, planning and code +2
Sensor Drift Compensation in Electronic-Nose-Based Gas Recognition Using Knowledge DistillationKnowledge distillation → Detection and dense prediction distillation
Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense ApproachDeep reinforcement learning methods → Adversarial robustness and RL in finance
Parallelism Meets Adaptiveness: Scalable Documents Understanding in Multi-Agent LLM SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
Pragmatic Policy Development via Interpretable Behavior CloningOffline RL and imitation learning from data → Safe offline RL +1
Shared Control of Holonomic Wheelchairs through Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
Toward Scalable Video Narration: A Training-free Approach Using Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Video understanding with MLLMs
Evaluating Uncertainty and Quality of Vision-Language-Action-enabled RobotsVision-language-action models → Failure recovery and robustness
Hierarchical Reinforcement Learning Framework for Adaptive Walking Control Using General Value Functions of Lower-Limb Sensor SignalsDeep reinforcement learning methods → RL for robot locomotion and manipulation
Leveraging Synthetic Data for Question Answering with Multilingual LLMs in the Agricultural DomainSynthetic data and self-improvement for LLMs → Synthetic reasoning data and bootstrapping
Text-to-SPARQL Goes Beyond English: Multilingual Question Answering Over Knowledge Graphs through Human-Inspired ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
Harnessing RLHF for Robust Unanswerability Recognition and Trustworthy Response Generation in LLMsLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
AURA: A Multi-Modal Medical Agent for Understanding, Reasoning & AnnotationLLM reasoning → Clinical and biomedical applications +1
SplitMeanFlow: Interval Splitting Consistency in Few-Step Generative ModelingDiffusion models → Flow matching, time series and science
Finding DoRI: Discovery of Retained Images in Diffusion ModelsDiffusion models → Diffusion foundations and sampling
CausalStep: A Benchmark for Explicit Stepwise Causal Reasoning in VideosLLM reasoning → Multimodal reasoning
Diffusion-Modeled Reinforcement Learning for Carbon and Risk-Aware Microgrid OptimizationDeep reinforcement learning methods → RL for energy, networks and operations
ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent PlanningLLM reasoning → Spatial and embodied reasoning +1
Semi-off-Policy Reinforcement Learning for Vision-Language Slow-Thinking ReasoningLLM reasoning → Multimodal reasoning +1
MegaScience: Pushing the Frontiers of Post-Training Datasets for Science ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
LingBench++: A Linguistically-Informed Benchmark and Reasoning Framework for Multi-Step and Cross-Cultural Inference with LLMsLLM reasoning → Reasoning benchmarks and evaluation
Beyond Binary Rewards: Training LMs to Reason About Their UncertaintyLLM reasoning → Reinforcement learning for reasoning +1
Agentar-Fin-R1: Enhancing Financial Intelligence through Domain Expertise, Training Efficiency, and Advanced ReasoningLLM reasoning → Reasoning for agents, planning and code
Test-Time-Matching: Decouple Personality, Memory, and Linguistic Style in LLM-based Role-Playing Language AgentLLM agents and tool use → Social simulation and multi-agent debate
Beyond Context Limits: Subconscious Threads for Long-Horizon ReasoningLLM reasoning → Test-time compute and efficient thinking
Never Come Up Empty: Adaptive HyDE Retrieval for Improving LLM Developer SupportRetrieval-augmented generation → RAG pipeline design and evaluation
Zebra-CoT: A Dataset for Interleaved Vision Language ReasoningLLM reasoning → Multimodal reasoning
Generative Diffusion Models for Wireless Networks: Fundamental, Architecture, and State-of-the-ArtDiffusion models → Diffusion for compression and wireless
HarmonPaint: Harmonized Training-Free Diffusion InpaintingDiffusion models → 3D, point cloud and scene generation
RAVine: Reality-Aligned Evaluation for Agentic SearchLLM agents and tool use → Web, search, and research agents
Enhancing Remote Sensing Vision-Language Models Through MLLM and LLM-Based High-Quality Image-Text Dataset GenerationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Advancing Risk and Quality Assurance: A RAG Chatbot for Improved Regulatory ComplianceRetrieval-augmented generation → RAG pipeline design and evaluation
PICACO: Pluralistic In-Context Value Alignment of LLMs via Total Correlation OptimizationLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment +1
Turning Internal Gap into Self-Improvement: Promoting the Generation-Understanding Unification in MLLMsSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
P-CoT: A Pedagogically-motivated Participatory Chain-of-Thought Prompting for Phonological Reasoning in LLMsLLM reasoning → Prompting and chain-of-thought reasoning
Hybrid Reward-Driven Reinforcement Learning for Efficient Quantum Circuit SynthesisDeep reinforcement learning methods → Quantum reinforcement learning
A2Mamba: Attention-augmented State Space Models for Visual RecognitionState-space sequence models (S4, Mamba) → Vision Mamba backbones
Pyramid Hierarchical Masked Diffusion Model for Imaging SynthesisDiffusion models → Medical imaging and segmentation
Pixels to Principles: Probing Intuitive Physics Understanding in Multimodal Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
EarthCrafter: Scalable 3D Earth Generation via Dual-Sparse Latent DiffusionDiffusion models → 3D, point cloud and scene generation
Spatial 3D-LLM: Exploring Spatial Awareness in 3D Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
SyncLoop: A Multimodal Dual-Loop Framework for Self-Improving Mathematical ReasoningLLM reasoning → Multimodal reasoning +2
Agentic RAG with Knowledge Graphs for Complex Multi-Hop Reasoning in Real-World ApplicationsLLM reasoning → Knowledge- and tool-augmented reasoning +2
Guided Reinforcement Learning for Omnidirectional 3D Jumping in Quadruped RobotsDeep reinforcement learning methods → RL for robot locomotion and manipulation
ACT: Bridging the Gap in Code Translation through Synthetic Data Generation & Adaptive TrainingSynthetic data and self-improvement for LLMs → Code and instruction data synthesis
Learning Temporal Abstractions via Variational Homomorphisms in Option-Induced Abstract MDPsLLM reasoning → Test-time compute and efficient thinking
Towards Enforcing Company Policy Adherence in Agentic WorkflowsLLM agents and tool use → Agent threats, guardrails and governance
Robust Noisy Pseudo-label Learning for Semi-supervised Medical Image Segmentation Using Diffusion ModelDiffusion models → Medical imaging and segmentation
ReasonVQA: A Multi-hop Reasoning Benchmark with Structural Knowledge for Visual Question AnsweringLLM reasoning → Multimodal reasoning
LLM-Driven Collaborative Model for Untangling Commits via Explicit and Implicit Dependency ReasoningLLM reasoning → Reasoning for agents, planning and code
Mamba-OTR: a Mamba-based Solution for Online Take and Release Detection from Untrimmed Egocentric VideoState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
Navigating Large-Pose Challenge for High-Fidelity Face Reenactment with Video Diffusion ModelDiffusion models → Audio, speech and music
DREAM: Scalable Red Teaming for Text-to-Image Generative Systems via Distribution ModelingLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
Towards Resilient Safety-driven Unlearning for Diffusion Models against Downstream Fine-tuningDiffusion models → Robustness, privacy and adversarial aspects +1
STAlloc: Enhancing Memory Efficiency in Large-Scale Model Training with Spatio-Temporal PlanningMixture-of-experts → Efficient MoE training and inference systems
iShumei-Chinchunmei at SemEval-2025 Task 4: A balanced forgetting and retention multi-task framework using effective unlearning lossLLM safety and security → Machine unlearning
Quality Text, Robust Vision: The Role of Language in Enhancing Visual Robustness of Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
Efficient RL for optimizing conversation level outcomes with an LLM-based tutorLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
FinResearchBench: A Logic Tree based Agent-as-a-Judge Evaluation Framework for Financial Research AgentsLLM agents and tool use → Financial trading and forecasting agents
Voice-based AI Agents: Filling the Economic Gaps in Digital Health DeliveryLLM agents and tool use → Medical and scientific domain agents
Distilled Large Language Model in Confidential Computing Environment for System-on-Chip DesignKnowledge distillation → Knowledge distillation for LLMs
LOCOFY Large Design Models -- Design to code conversion solutionMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
EBaReT: Expert-guided Bag Reward Transformer for Auto BiddingDeep reinforcement learning methods → RL theory and sample complexity
Emergent Cognitive Convergence via Implementation: Structured Cognitive Loop Reflecting Four Theories of MindLLM agents and tool use → General LLM agent frameworks and benchmarks
AtrousMamaba: An Atrous-Window Scanning Visual State Space Model for Remote Sensing Change DetectionState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
LSSGen: Leveraging Latent Space Scaling in Flow and Diffusion for Efficient Text to Image GenerationDiffusion models → Diffusion foundations and sampling
Equivariant Goal Conditioned Contrastive Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
Pusa V1.0: Unlocking Temporal Control in Pretrained Video Diffusion Models via Vectorized Timestep AdaptationDiffusion models → Video generation
GOAT: A Large Dataset of Paired Guitar Audio Recordings and Tablatures
Argument Quality Annotation and Gender Bias Detection in Financial Communication through Large Language Models
Tell Me Without Telling Me: Two-Way Prediction of Visualization Literacy and Visual Attention
How Deep Is Representational Bias in LLMs? The Cases of Caste and Religion
A Social Data-Driven System for Identifying Estate-related Events and Topics
Evaluating Generative AI Tools for Personalized Offline Recommendations: A Comparative Study
Benchmarking Classical and Quantum Models for DeFi Yield Prediction on Curve Finance
Satellite Connectivity Prediction for Fast-Moving Platforms
A Data-Driven Machine Learning Approach for Predicting Axial Load Capacity in Steel Storage Rack Columns
Preliminary suggestions for rigorous GPAI model evaluations
Test-time Prompt Refinement for Text-to-Image Models
TTS-1 Technical Report
Toward a Universal Characterization of Sudoku Puzzle Difficulty
Beyond Correlation: Learning Supervised, Sample-Distinct, and Eigenimage-Interpretable Representations
Quantum Geometry of Data
Analysis of Threat-Based Manipulation in Large Language Models: A Dual Perspective on Vulnerabilities and Performance Enhancement Opportunities
NPO: Learning Alignment and Meta-Alignment through Structured Human Feedback
INTEGRALBENCH: Benchmarking LLMs with Definite Integral Problems
Bayesian symbolic regression: Automated equation discovery from a physicists' perspective
Swift-Sarsa: Fast and Robust Linear Control
Mind the Language Gap in Digital Humanities: LLM-Aided Translation of SKOS Thesauri
Graph Learning Metallic Glass Discovery from Wikipedia
FedDPG: An Adaptive Yet Efficient Prompt-tuning Approach in Federated Learning Settings
ShrinkBox: Backdoor Attack on Object Detection to Disrupt Collision Avoidance in Machine Learning-based Advanced Driver Assistance Systems

All 337