Papers

New on arXiv

Tue 4 Feb 2025

376 papers

Scaling Natural-Language Graph-Based Test Time Compute for Automated Theorem ProvingLLM reasoning → Mathematical reasoning
Spatial-RAG: Spatial Retrieval Augmented Generation for Real-World Geospatial Reasoning QuestionsLLM reasoning → Spatial and embodied reasoning +1
Position: Stop Acting Like Language Model Agents Are Normal AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
Diffusion Instruction TuningMultimodal LLMs / vision-language models → Medical vision-language models +1
Policy Guided Tree Search for Enhanced LLM ReasoningLLM reasoning → Test-time compute and efficient thinking
Harness Local Rewards for Global Benefits: Effective Text-to-Video Generation Alignment with Patch-level Reward ModelsDiffusion models → Video generation +1
Watermarking across Modalities for Content Tracing and Generative AILLM safety and security → Watermarking generated content and models
DERMARK: A Dynamic, Efficient and Robust Multi-bit Watermark for Large Language ModelsLLM safety and security → Watermarking generated content and models
Exploring Spatial Language Grounding Through Referring ExpressionsLLM reasoning → Spatial and embodied reasoning +1
Position: Scaling LLM Agents Requires Asymptotic Analysis with LLM PrimitivesLLM agents and tool use → General LLM agent frameworks and benchmarks
Reusing Embeddings: Reproducible Reward Model Research in Large Language Model Alignment without GPUsLLM reasoning → Reinforcement learning for reasoning +1
Reviving The Classics: Active Reward Modeling in Large Language Model AlignmentLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
Investigating the Robustness of Deductive Reasoning with Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
CodeSteer: Symbolic-Augmented Language Models via Code/Text GuidanceLLM reasoning → Reasoning for agents, planning and code
Multi-Lingual Cyber Threat Detection in Tweets/X Using ML, DL, and LLM: A Comparative AnalysisLLM safety and security → Prompt injection and agent security
Jingfang: An LLM-Based Multi-Agent System for Precise Medical Consultation and Syndrome Differentiation in Traditional Chinese MedicineLLM agents and tool use → Medical and scientific domain agents
Classroom Simulacra: Building Contextual Student Generative Agents in Online Education for Learning Behavioral SimulationLLM agents and tool use → Educational agents and math problem solving
When are Diffusion Priors Helpful in Sparse Reconstruction? A Study with Sparse-view CTDiffusion models → Medical imaging and segmentation
PatchPilot: A Cost-Efficient Software Engineering Agent with Early Attempts on Formal VerificationLLM agents and tool use → Software engineering coding agents
Vision-Language Model Dialog Games for Self-ImprovementMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
A Unified Understanding and Evaluation of Steering MethodsMechanistic interpretability → Activation steering methods
LadderMIL: Multiple Instance Learning with Coarse-to-Fine Self-DistillationKnowledge distillation → Distillation for medical imaging
On Teacher Hacking in Language Model DistillationLLM alignment / RLHF / preference optimisation → Reward hacking and misspecification +1
Deep Reinforcement Learning Enabled Persistent Surveillance with Energy-Aware UAV-UGV Systems for Disaster Management ApplicationsDeep reinforcement learning methods → RL for robot navigation and UAV control
e-SimFT: Alignment of Generative Models with Simulation Feedback for Pareto-Front Design ExplorationLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
Regret-Optimized Portfolio Enhancement through Deep Reinforcement Learning and Future Looking RewardsDeep reinforcement learning methods → Adversarial robustness and RL in finance
PolarQuant: Quantizing KV Caches with Polar TransformationEfficient LLM inference and serving → KV cache quantization
Calibrated Multi-Preference Optimization for Aligning Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics +1
QLASS: Boosting Language Agent Inference via Q-Guided Stepwise SearchLLM reasoning → Reasoning for agents, planning and code +1
Open Materials Generation with Stochastic InterpolantsDiffusion models → Flow matching, time series and science
Themis: Efficient Sparse Model Training Through Fully Sharded Sparse Data ParallelismMixture-of-experts → Efficient MoE training and inference systems
OverThink: Slowdown Attacks on Reasoning LLMsLLM reasoning → Reasoning for agents, planning and code
Flow Q-LearningDiffusion models → Diffusion and flow policies for robotics +1
Adaptive Self-improvement LLM Agentic System for ML Library DevelopmentLLM agents and tool use → Software engineering coding agents +1
Multi-Agent Design: Optimizing Agents with Better Prompts and TopologiesLLM agents and tool use → General LLM agent frameworks and benchmarks
Diff9D: Diffusion-Based Domain-Generalized Category-Level 9-DoF Object Pose EstimationDiffusion models → 3D, point cloud and scene generation
Brief analysis of DeepSeek R1 and its implications for Generative AILLM reasoning → Reasoning benchmarks and evaluation +1
Privacy Attacks on Image AutoRegressive ModelsDiffusion models → Robustness, privacy and adversarial aspects
Diffusion Generative Modeling on Lie Group RepresentationsDiffusion models → Flow matching, time series and science
Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive SearchLLM reasoning → Reinforcement learning for reasoning
EasySpec: Layer-Parallel Speculative Decoding for Efficient Multi-GPU UtilizationEfficient LLM inference and serving → Speculative decoding
Do Graph Diffusion Models Accurately Capture and Generate Substructure Distributions?Diffusion models → Flow matching, time series and science
Distributional Diffusion Models with Scoring RulesDiffusion models → Diffusion foundations and sampling
Rankify: A Comprehensive Python Toolkit for Retrieval, Re-Ranking, and Retrieval-Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
SAISA: Towards Multimodal Large Language Models with Both Training and Inference EfficiencyMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Personalization Toolkit: Training Free Personalization of Large Vision Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
Lower Bounds for Chain-of-Thought Reasoning in Hard-Attention TransformersLLM reasoning → Prompting and chain-of-thought reasoning
CoAT: Chain-of-Associated-Thoughts Framework for Enhancing Large Language Models ReasoningLLM reasoning → Test-time compute and efficient thinking
STAIR: Improving Safety Alignment with Introspective ReasoningLLM reasoning → Reasoning for agents, planning and code +2
Premise-Augmented Reasoning Chains Improve Error Identification in Math reasoning with LLMsLLM reasoning → Mathematical reasoning
AStar: Boosting Multimodal Reasoning with Automated Structured ThinkingLLM reasoning → Multimodal reasoning +1
Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
Policy-Guided Causal State Representation for Offline Reinforcement Learning RecommendationOffline RL and imitation learning from data → Decision transformers and sequence modeling
DIME:Diffusion-Based Maximum Entropy Reinforcement LearningDiffusion models → Diffusion and flow policies for robotics +1
MAGNNET: Multi-Agent Graph Neural Network-based Efficient Task Allocation for Autonomous Vehicles with Deep Reinforcement LearningEnd-to-end autonomous driving → Cooperative and V2X driving
Real-Time Operator Takeover for Visuomotor Diffusion Policy TrainingDiffusion models → Diffusion and flow policies for robotics
Information-Theoretic Proofs for Diffusion SamplingDiffusion models → Diffusion foundations and sampling
Adviser-Actor-Critic: Eliminating Steady-State Error in Reinforcement Learning ControlDeep reinforcement learning methods → RL theory and sample complexity
Conversation AI Dialog for Medicare powered by Finetuning and Retrieval Augmented GenerationRetrieval-augmented generation → Medical and biomedical RAG
Exploring the latent space of diffusion models directly through singular value decompositionDiffusion models → Diffusion foundations and sampling
InterLCM: Low-Quality Images as Intermediate States of Latent Consistency Models for Effective Blind Face RestorationDiffusion models → Inverse problems and image restoration
On the Expressivity of Selective State-Space Layers: A Multivariate Polynomial ApproachState-space sequence models (S4, Mamba) → Core SSM architectures for language
From Uncertain to Safe: Conformal Adaptation of Diffusion Models for Safe PDE ControlDiffusion models → Diffusion and flow policies for robotics
VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token CachingLLM reasoning → Spatial and embodied reasoning +1
Vulnerability Mitigation for Safety-Aligned Language Models via DebiasingLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
On the Guidance of Flow MatchingDiffusion models → Flow matching, time series and science
From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving ScenariosEnd-to-end autonomous driving → Adversarial scenarios and safety testing
Synthesis of Model Predictive Control and Reinforcement Learning: Survey and ClassificationDeep reinforcement learning methods → RL for autonomous driving and traffic
Dual-IPO: Dual-Iterative Preference Optimization for Text-to-Video GenerationDiffusion models → Video generation +1
Rethinking stance detection: A theoretically-informed research agenda for user-level inference using language modelsLLM reasoning → Causal reasoning in LLMs
LoRA-TTT: Low-Rank Test-Time Training for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Robust and Secure Code Watermarking for Large Language Models via ML/Crypto CodesignLLM safety and security → Watermarking generated content and models
Reason4Rec: Deliberative User Preference Alignment of Large Language Models for RecommendationLLM reasoning → LLM reasoning for recommendation
RAPID: Robust and Agile Planner Using Inverse Reinforcement Learning for Vision-Based Drone NavigationOffline RL and imitation learning from data → Imitation learning methods
M2R2: Mixture of Multi-Rate Residuals for Efficient Transformer InferenceMixture-of-experts → Efficient MoE training and inference systems +1
UD-Mamba: A pixel-level uncertainty-driven Mamba model for medical image segmentationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
Analytical Lyapunov Function Discovery: An RL-based Generative ApproachDeep reinforcement learning methods → RL theory and sample complexity
Reasoning Bias of Next Token Prediction TrainingLLM reasoning → Test-time compute and efficient thinking
One Diffusion Step to Real-World Super-Resolution via Flow Trajectory DistillationDiffusion models → Inverse problems and image restoration
Rethinking Timesteps Samplers and Prediction TypesDiffusion models → Diffusion foundations and sampling
VFScale: Intrinsic Reasoning through Verifier-Free Test-time Scalable Diffusion ModelLLM reasoning → Diffusion reasoning and test-time scaling +1
Generative Data Mining with Longtail-Guided DiffusionDiffusion models → Diffusion foundations and sampling
AutoGUI: Scaling GUI Grounding with Automatic Functionality Annotations from LLMsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Mitigating Object Hallucinations in Large Vision-Language Models via Attention CalibrationLLM reasoning → Hallucination detection and mitigation +1
MPIC: Position-Independent Multimodal Context Caching System for Efficient MLLM ServingMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
DHP: Discrete Hierarchical Planning for Hierarchical Reinforcement Learning AgentsDeep reinforcement learning methods → Deep RL algorithms and representations
DAMA: Data- and Model-aware Alignment of Multi-modal LLMsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
Semantic Integrity Matters: Benchmarking and Preserving High-Density Reasoning in KV Cache CompressionLLM reasoning → Test-time compute and efficient thinking +1
VolleyBots: A Testbed for Multi-Drone Volleyball Game Combining Motion Control and Strategic PlayDeep reinforcement learning methods → Multi-agent reinforcement learning
Robust LLM Alignment via Distributionally Robust Direct Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
PANDAS: Improving Many-shot Jailbreaking via Positive Affirmation, Negative Demonstration, and Adaptive SamplingLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
Complying with the EU AI Act: Innovations in Explainable and User-Centric Hand Gesture Recognition
Exploring the Panorama of Anxiety Levels: A Multi-Scenario Study Based on Human-Centric Anxiety Level Detection and Personalized Guidance
TRUTH DECAY: Quantifying Multi-Turn Sycophancy in Language Models
A Framework for Responsible AI Systems: Building Societal Trust through Domain Definition, Trustworthy AI Design, Auditability, Accountability, and Governance
Copyright in AI-generated works: Lessons from recent developments in patent law
FinBloom: Knowledge Grounding Large Language Model with Real-time Financial Data
IncepFormerNet: A multi-scale multi-head attention network for SSVEP classification
Causal Language in Observational Studies: Sociocultural Backgrounds and Team Composition

All 376