Papers

New on arXiv

Mon 23 Jun 2025

346 papers

Accelerated Portfolio Optimization and Option Pricing with Reinforcement LearningDeep reinforcement learning methods → Adversarial robustness and RL in finance
Can Argus Judge Them All? Comparing VLMs Across DomainsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
CaughtCheating: Is Your MLLM a Good Cheating Detective? Exploring the Boundary of Visual Perception and ReasoningLLM reasoning → Multimodal reasoning +2
AI Agents-as-Judge: Automated Assessment of Accuracy, Consistency, Completeness and Clarity for Enterprise DocumentsLLM agents and tool use → General LLM agent frameworks and benchmarks
Optimal Design of Experiment for Electrochemical Parameter Identification of Li-ion Battery via Deep Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
Thought Anchors: Which LLM Reasoning Steps Matter?LLM reasoning → Prompting and chain-of-thought reasoning
Local Learning Rules for Out-of-Equilibrium Physical Generative ModelsDiffusion models → Diffusion foundations and sampling
CUPID: Curating Data your Robot Loves with Influence FunctionsOffline RL and imitation learning from data → Robot manipulation imitation learning
PrITTI: Primitive-based Generation of Controllable and Editable 3D Semantic Urban ScenesWorld models → World models for autonomous driving +1
Enhancing Security in LLM Applications: A Performance Evaluation of Early Detection SystemsLLM safety and security → Prompt injection and agent security
Inverse-and-Edit: Effective and Fast Image Editing by Cycle Consistency ModelsDiffusion models → Image generation, text-to-image and editing
Baba is LLM: Reasoning in a Game with Dynamic RulesLLM reasoning → Reasoning for agents, planning and code
Language Models Might Not Understand You: Evaluating Theory of Mind via Story PromptingWorld models → World models for language agents
FairCauseSyn: Towards Causally Fair LLM-Augmented Synthetic Data GenerationSynthetic data and self-improvement for LLMs → Privacy-preserving tabular data synthesis
Reading Smiles: Proxy Bias in Foundation Models for Facial Emotion RecognitionMultimodal LLMs / vision-language models → Multimodal emotion understanding
MFTCXplain: A Multilingual Benchmark Dataset for Evaluating the Moral Reasoning of LLMs through Multi-hop Hate Speech ExplanationLLM reasoning → Reasoning benchmarks and evaluation
HAWAII: Hierarchical Visual Knowledge Transfer for Efficient Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Plan for Speed: Dilated Scheduling for Masked Diffusion Language ModelsDiffusion models → Discrete and text diffusion
When Diffusion Models Memorize: Inductive Biases in Probability Flow of Minimum-Norm Shallow Neural NetsDiffusion models → Diffusion foundations and sampling
Diffusion Transformer-to-Mamba Distillation for High-Resolution Image GenerationDiffusion models → Medical imaging and segmentation +1
GLIMPSE: Holistic Cross-Modal Explainability for Large Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning AgentsLLM reasoning → Knowledge- and tool-augmented reasoning +1
A Comment On "The Illusion of Thinking": Reframing the Reasoning Cliff as an Agentic GapLLM reasoning → Test-time compute and efficient thinking +1
DiffRIS: Enhancing Referring Remote Sensing Image Segmentation with Pre-trained Text-to-Image Diffusion ModelsDiffusion models → Inverse problems and image restoration
Chain-of-Experts: Unlocking the Communication Power of Mixture-of-Experts ModelsMixture-of-experts → Expert routing strategies
Audit & Repair: An Agentic Framework for Consistent Story Visualization in Text-to-Image Diffusion ModelsDiffusion models → Image generation, text-to-image and editing +1
Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned RepresentationsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
MinD: Learning A Dual-System World Model for Real-Time Planning and Implicit Risk AnalysisWorld models → Embodied and robot world models +2
ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMsLLM reasoning → Reinforcement learning for reasoning +1
Steering Conceptual Bias via Transformer Latent-Subspace ActivationMechanistic interpretability → Activation steering methods
Universal Video Temporal Grounding with Generative Multi-modal Large Language ModelsMultimodal LLMs / vision-language models → Video understanding with MLLMs
OMEGA: Can LLMs Reason Outside the Box in Math? Evaluating Exploratory, Compositional, and Transformative GeneralizationLLM reasoning → Mathematical reasoning
CommVQ: Commutative Vector Quantization for KV Cache CompressionEfficient LLM inference and serving → KV cache quantization
Mechanistic Interpretability Needs PhilosophyMechanistic interpretability → Circuits and mechanistic analysis
Offline Goal-Conditioned Reinforcement Learning with Projective Quasimetric PlanningOffline RL and imitation learning from data → Diffusion and flow policies for offline RL
Adaptive Activation Steering for Efficient LLM Reasoning via Closed-Loop PID ControlLLM reasoning → Test-time compute and efficient thinking +1
SViP: Sequencing Bimanual Visuomotor Policies with Object-Centric Motion PrimitivesOffline RL and imitation learning from data → Robot manipulation imitation learning
Understanding Software Engineering Agents: A Study of Thought-Action-Result TrajectoriesLLM reasoning → Reasoning for agents, planning and code +1
ConciseHint: Boosting Efficient Reasoning via Continuous Concise Hints during GenerationLLM reasoning → Test-time compute and efficient thinking
ViDAR: Video Diffusion-Aware 4D Reconstruction From Monocular InputsDiffusion models → 3D, point cloud and scene generation
Shift Happens: Mixture of Experts based Continual Adaptation in Federated LearningMixture-of-experts → Federated mixture-of-experts
TRIZ Agents: A Multi-Agent LLM Approach for TRIZ-Based InnovationLLM agents and tool use → General LLM agent frameworks and benchmarks
Existing LLMs Are Not Self-Consistent For Simple TasksLLM reasoning → Test-time compute and efficient thinking
DiffDef: A Diffusion Model for Generating Multimodal Goal Shapes From Demonstrations for Deformable Object ManipulationDiffusion models → Diffusion and flow policies for robotics
ContinualFlow: Learning and Unlearning with Neural Flow MatchingDiffusion models → Flow matching, time series and science +1
An Audio-centric Multi-task Learning Framework for Streaming Ads Targeting on SpotifyMixture-of-experts → MoE for recommender systems
PARALLELPROMPT: Extracting Parallelism from Large Language Model QueriesEfficient LLM inference and serving → Prompt and context compression
Multi-modal Anchor Gated Transformer with Knowledge Distillation for Emotion Recognition in ConversationKnowledge distillation → Multimodal distillation
TCDiff++: An End-to-end Trajectory-Controllable Diffusion Model for Harmonious Music-Driven Group ChoreographyDiffusion models → Audio, speech and music
RDPO: Real Data Preference Optimization for Physics Consistency Video GenerationLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
ReDit: Reward Dithering for Improved LLM Policy OptimizationLLM reasoning → Reinforcement learning for reasoning
AggTruth: Contextual Hallucination Detection using Aggregated Attention Scores in LLMsRetrieval-augmented generation → Hallucination detection in RAG
Efficient and Robust Speaker Diarization via Structured Pruning of Self-Supervised ModelsKnowledge distillation → Speech and audio distillation
Policy gradient methods for ordinal policiesDeep reinforcement learning methods → RL theory and sample complexity
No Training Wheels: Steering Vectors for Bias Correction at Inference TimeMechanistic interpretability → Probing deception, bias and beliefs
Parallel Continuous Chain-of-Thought with Jacobi IterationLLM reasoning → Prompting and chain-of-thought reasoning
A Modular Taxonomy for Hate Speech Definitions and Its Impact on Zero-Shot LLM Classification PerformanceLLM safety and security → Safety alignment, refusal and guardrails
Efficient Beam Selection for ISAC in Cell-Free Massive MIMO via Digital Twin-Assisted Deep Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
T-CPDL: A Temporal Causal Probabilistic Description Logic for Developing Logic-RAG AgentRetrieval-augmented generation → Agentic RAG, agents and memory +1
SoK: A Comprehensive Security Analysis of Jailbreak Resilience in GPT and DeepSeek ModelsLLM safety and security → Jailbreaking
Transformer World Model for Sample Efficient Multi-Agent Reinforcement LearningWorld models → Latent dynamics models and model-based RL
MedTVT-R1: A Multimodal LLM Empowering Medical Reasoning and DiagnosisLLM reasoning → Clinical and biomedical applications +1
Standard Applicability Judgment and Cross-jurisdictional Reasoning: A RAG-based Framework for Medical Device ComplianceLLM reasoning → Clinical and biomedical applications
Generalizing vision-language models to novel domains: A comprehensive surveyMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Distilling Balanced Knowledge from a Biased TeacherKnowledge distillation → General knowledge distillation methods
A Simple "Motivation" Can Enhance Reinforcement Finetuning of Large Reasoning ModelsLLM reasoning → Reinforcement learning for reasoning
GANs vs. Diffusion Models for virtual staining with the HER2match datasetDiffusion models → Medical imaging and segmentation
Reliability-Adjusted Prioritized Experience ReplayDeep reinforcement learning methods → Deep RL algorithms and representations
Context Consistency Learning via Sentence Removal for Semi-Supervised Video Paragraph GroundingKnowledge distillation → Multimodal distillation
AViLA: Asynchronous Vision-Language Agent for Streaming Multimodal Data InteractionLLM agents and tool use → Multimodal and embodied agents
CPAM: Context-Preserving Adaptive Manipulation for Zero-Shot Real Image EditingDiffusion models → Image generation, text-to-image and editing
How Robust is Model Editing after Fine-Tuning? An Empirical Study on Text-to-Image Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
TReB: A Comprehensive Benchmark for Evaluating Table Reasoning Capabilities of Large Language ModelsLLM reasoning → Knowledge- and tool-augmented reasoning
Generative Diffusion Receivers: Achieving Pilot-Efficient MIMO-OFDM CommunicationsDiffusion models → Diffusion for compression and wireless
InternSpatial: A Comprehensive Dataset for Spatial Reasoning in Vision-Language ModelsLLM reasoning → Spatial and embodied reasoning +1
LOGICPO: Efficient Translation of NL-based Logical Problems to FOL using LLMs and Preference OptimizationLLM reasoning → Reasoning benchmarks and evaluation +1
Taming Vision-Language Models for Medical Image Analysis: A Comprehensive ReviewMultimodal LLMs / vision-language models → Medical vision-language models
RePIC: Reinforced Post-Training for Personalizing Multi-Modal Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
SlimMoE: Structured Compression of Large MoE Models via Expert Slimming and DistillationMixture-of-experts → MoE large language models
Dynamic Knowledge Exchange and Dual-diversity Review: Concisely Unleashing the Potential of a Multi-Agent Research TeamLLM agents and tool use → Web, search, and research agents
BSMamba: Brightness and Semantic Modeling for Long-Range Interaction in Low-Light Image EnhancementState-space sequence models (S4, Mamba) → Mamba for image restoration
Less Data Less Tokens: Multilingual Unification Learning for Efficient Test-Time Reasoning in LLMsLLM reasoning → Reasoning benchmarks and evaluation
Controlled Generation with Equivariant Variational Flow MatchingDiffusion models → Flow matching, time series and science
End-to-End Fine-Tuning of 3D Texture Generation using Differentiable RewardsLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
Confucius3-Math: A Lightweight High-Performance Reasoning LLM for Chinese K-12 Mathematics LearningLLM reasoning → Reinforcement learning for reasoning
NSFW-Classifier Guided Prompt Sanitization for Safe Text-to-Image GenerationLLM safety and security → Vision-language and text-to-image safety
Escaping the SpuriVerse: Can Large Vision-Language Models Generalize Beyond Seen Spurious Correlations?Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Sharpening the Spear: Adaptive Expert-Guided Adversarial Attack Against DRL-based Autonomous Driving PoliciesEnd-to-end autonomous driving → Adversarial scenarios and safety testing +1
Advanced For-Loop for QML algorithm searchLLM agents and tool use → Medical and scientific domain agents
RLPR: Extrapolating RLVR to General Domains without VerifiersLLM reasoning → Reinforcement learning for reasoning
Morse: Dual-Sampling for Lossless Acceleration of Diffusion ModelsDiffusion models → Diffusion foundations and sampling
Smart-LLaMA-DPO: Reinforced Large Language Model for Explainable Smart Contract Vulnerability DetectionLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks
Dual-Forward Path Teacher Knowledge Distillation: Bridging the Capacity Gap Between Teacher and StudentKnowledge distillation → General knowledge distillation methods
AdapThink: Adaptive Thinking Preferences for Reasoning Language ModelLLM reasoning → Test-time compute and efficient thinking +1
Drive-R1: Bridging Reasoning and Planning in VLMs for Autonomous Driving with Reinforcement LearningLLM reasoning → Chain-of-thought reasoning for driving +2
Make It Efficient: Dynamic Sparse Attention for Autoregressive Image GenerationEfficient LLM inference and serving → Fast autoregressive visual generation
Cross-Architecture Knowledge Distillation (KD) for Retinal Fundus Image Anomaly Detection on NVIDIA Jetson NanoKnowledge distillation → Distillation for medical imaging
A Survey of AIOps in the Era of Large Language Models
A Machine Learning Framework for Breast Cancer Treatment Classification Using a Novel Dataset
Online Continual Learning via Spiking Neural Networks with Sleep Enhanced Latent Replay

All 346