Papers

New on arXiv

Fri 15 Aug 2025

255 papers

TTF-VLA: Temporal Token Fusion via Pixel-Attention Integration for Vision-Language-Action ModelsVision-language-action models → Efficient VLA inference and adaptation
Learn to Memorize: Optimizing LLM-based Agents with Adaptive Memory FrameworkLLM agents and tool use → Agent memory systems
From Clicks to Preference: A Multi-stage Alignment Framework for Generative Query Suggestion in Conversational SystemLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
Hard Examples Are All You Need: Maximizing GRPO Post-Training Under Annotation BudgetsLLM reasoning → Reinforcement learning for reasoning
Finite Automata Extraction: Low-data World Model Learning as Programs from Gameplay VideoWorld models → Video-generation world models and simulators
Every 28 Days the AI Dreams of Soft Skin and Burning Stars: Scaffolding AI Agents with Hormones and EmotionsLLM agents and tool use → Social simulation and multi-agent debate
Rethinking Autonomy: Preventing Failures in AI-Driven Software EngineeringLLM reasoning → Reasoning for agents, planning and code +1
Audio Flamingo Sound-CoT Technical Report: Improving Chain-of-Thought Reasoning in Sound UnderstandingLLM reasoning → Audio-language model reasoning +1
Labels or Input? Rethinking Augmentation in Multimodal Hate DetectionLLM reasoning → Reasoning benchmarks and evaluation
VideoAVE: A Multi-Attribute Video-to-Text Attribute Value Extraction Dataset and Benchmark ModelsMixture-of-experts → Vision mixture-of-experts
Uncalibrated Reasoning: GRPO Induces Overconfidence for Stochastic OutcomesLLM reasoning → Reinforcement learning for reasoning
Behavioral and Symbolic Fillers as Delay Mitigation for Embodied Conversational Agents in Virtual RealityLLM agents and tool use → Social simulation and multi-agent debate
Limitation Learning: Catching Adverse Dialog with GAILOffline RL and imitation learning from data → Language-conditioned policies and VLAs
Can we Evaluate RAGs with Synthetic Data?Synthetic data and self-improvement for LLMs → LLM synthetic data generation
Ovis2.5 Technical ReportLLM reasoning → Multimodal reasoning
SafeSieve: From Heuristics to Experience in Progressive Pruning for LLM-based Multi-Agent CommunicationLLM agents and tool use → General LLM agent frameworks and benchmarks
Thyme: Think Beyond ImagesLLM reasoning → Multimodal reasoning
LoRAtorio: An intrinsic approach to LoRA Skill CompositionDiffusion models → Image generation, text-to-image and editing
Controlling Multimodal LLMs via Reward-guided DecodingMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
Aware First, Think Less: Dynamic Boundary Self-Awareness Drives Extreme Reasoning Efficiency in Large Language ModelsLLM reasoning → Test-time compute and efficient thinking
SeamlessFlow: A Trainer Agent Isolation RL Framework Achieving Bubble-Free Pipelines via Tag SchedulingDeep reinforcement learning methods → RL training of language and agent models
Training-Free Anomaly Generation via Dual-Attention Enhancement in Diffusion ModelDiffusion models → Flow matching, time series and science
Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and TrendsLLM safety and security → Watermarking generated content and models
Reinforcing Video Reasoning Segmentation to Think Before It SegmentsLLM reasoning → Multimodal reasoning
Physics-Informed Diffusion Models for Unsupervised Anomaly Detection in Multivariate Time SeriesDiffusion models → Flow matching, time series and science
Semi-Supervised Learning with Online Knowledge Distillation for Skin Lesion ClassificationKnowledge distillation → Distillation for medical imaging
Sim2Dust: Mastering Dynamic Waypoint Tracking on Granular MediaDeep reinforcement learning methods → RL for robot navigation and UAV control
Perception in Plan: Coupled Perception and Planning for End-to-End Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture
CineTrans: Learning to Generate Videos with Cinematic Transitions via Masked Diffusion ModelsDiffusion models → Video generation
SPG: Style-Prompting Guidance for Style-Specific Content CreationDiffusion models → Image generation, text-to-image and editing
EvoPSF: Online Evolution of Autonomous Driving Models via Planning-State FeedbackEnd-to-end autonomous driving → Imitation-learning end-to-end planners
Inclusion Arena: An Open Platform for Evaluating Large Foundation Models with Real-World AppsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
MM-R1: Unleashing the Power of Unified Multimodal Large Language Models for Personalized Image GenerationLLM reasoning → Multimodal reasoning +1
ImagiDrive: A Unified Imagination-and-Planning Framework for Autonomous DrivingEnd-to-end autonomous driving → Generative simulation for driving
Tapas Are Free! Training-Free Adaptation of Programmatic Agents via LLM-Guided Program Synthesis in Dynamic EnvironmentsLLM agents and tool use → Agent threats, guardrails and governance
AIM-Bench: Evaluating Decision-making Biases of Agentic LLM as Inventory ManagerLLM reasoning → Reasoning for agents, planning and code +1
Survey-to-Behavior: Downstream Alignment of Human Values in LLMs via Survey QuestionsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic WeightingDeep reinforcement learning methods → RL training of language and agent models
FACET: Teacher-Centred LLM-Based Multi-Agent Systems-Towards Personalized Educational WorksheetsLLM agents and tool use → Educational agents and math problem solving
Trustworthy AI Psychotherapy: Multi-Agent LLM Workflow for Counseling and Explainable Mental Disorder DiagnosisLLM agents and tool use → Medical and scientific domain agents
Retrieval-augmented reasoning with lean language modelsLLM reasoning → Knowledge- and tool-augmented reasoning +1
Unified Knowledge Distillation Framework: Fine-Grained Alignment and Geometric Relationship Preservation for Deep Face RecognitionKnowledge distillation → General knowledge distillation methods
Fusing Rewards and Preferences in Reinforcement LearningLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
HOID-R1: Reinforcement Learning for Open-World Human-Object Interaction Detection Reasoning with Multimodal Large Language ModelLLM reasoning → Multimodal reasoning +1
Noise Matters: Optimizing Matching Noise for Diffusion ClassifiersMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
MoE-TTS: Enhancing Out-of-Domain Text Understanding for Description-based TTS via Mixture-of-ExpertsMixture-of-experts → MoE large language models
Logic Unseen: Revealing the Logical Blindspots of Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
SafeConstellations: Mitigating Over-Refusals in LLMs Through Task-Aware Representation SteeringLLM safety and security → Safety alignment, refusal and guardrails +1
LETToT: Label-Free Evaluation of Large Language Models On Tourism Using Expert Tree-of-ThoughtLLM reasoning → Spatial and embodied reasoning
Probing the Representational Power of Sparse Autoencoders in Vision ModelsDiffusion models → Image generation, text-to-image and editing +1
Enhancing Supervised Composed Image Retrieval via Reasoning-Augmented Representation EngineeringLLM reasoning → Multimodal reasoning +1
Vision-Language Models display a strong gender biasMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
UNVEILING: What Makes Linguistics Olympiad Puzzles Tricky for LLMs?LLM reasoning → Reasoning benchmarks and evaluation
FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait AnimationLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
Beyond Solving Math Quiz: Evaluating the Ability of Large Reasoning Models to Ask for InformationLLM reasoning → Mathematical reasoning
Cross-Granularity Hypergraph Retrieval-Augmented Generation for Multi-hop Question AnsweringRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
RAG for Geoscience: What We Expect, Gaps and OpportunitiesRetrieval-augmented generation → RAG pipeline design and evaluation
ORFuzz: Fuzzing the "Other Side" of LLM Safety -- Testing Over-RefusalLLM safety and security → Safety alignment, refusal and guardrails
A CLIP-based Uncertainty Modal Modeling (UMM) Framework for Pedestrian Re-Identification in Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture
A Coarse-to-Fine Human Pose Estimation Method based on Two-stage Distillation and Progressive Graph Neural NetworkKnowledge distillation → Detection and dense prediction distillation
Efficient Image-to-Image Schr"odinger Bridge for CT Field of View ExtensionDiffusion models → Medical imaging and segmentation
Multi-Group Equivariant Augmentation for Reinforcement Learning in Robot ManipulationDeep reinforcement learning methods → RL for robot locomotion and manipulation
Visuomotor Grasping with World Models for Surgical RobotsWorld models → Medical and surgical world models
UAV-VL-R1: Generalizing Vision-Language Models via Supervised Fine-Tuning and Multi-Stage GRPO for UAV Visual ReasoningLLM reasoning → Spatial and embodied reasoning +1
Fine-Grained VLM Fine-tuning via Latent Hierarchical Adapter LearningMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Better Supervised Fine-tuning for VQA: Integer-Only LossMultimodal LLMs / vision-language models → Image editing and quality assessment
Semi-supervised Image Dehazing via Expectation-Maximization and Bidirectional Brownian Bridge Diffusion ModelsDiffusion models → Inverse problems and image restoration
Role-Augmented Intent-Driven Generative Search Engine OptimizationRetrieval-augmented generation → RAG pipeline design and evaluation
AlphaAgents: Large Language Model based Multi-Agents for Equity Portfolio ConstructionsLLM agents and tool use → Financial trading and forecasting agents
Actor-Critic for Continuous Action Chunks: A Reinforcement Learning Framework for Long-Horizon Robotic Manipulation with Sparse RewardDeep reinforcement learning methods → RL for robot locomotion and manipulation
Residual-based Efficient Bidirectional Diffusion Model for Image Dehazing and Haze GenerationDiffusion models → Inverse problems and image restoration
MoNaCo: More Natural and Complex Questions for Reasoning Across Dozens of DocumentsLLM reasoning → Knowledge- and tool-augmented reasoning
AI Agentic Programming: A Survey of Techniques, Challenges, and OpportunitiesLLM agents and tool use → Software engineering coding agents
The 1st International Workshop on Disentangled Representation Learning for Controllable Generation (DRL4Real): Methods and Results
Forecasting Clicks in Digital Advertising: Multimodal Inputs and Interpretable Outputs
CERA: A Framework for Improved Generalization of Machine Learning Models to Changed Climates
Optimized Renewable Energy Planning MDP for Socially-Equitable Electricity Coverage in the US
Emotional Manipulation by AI Companions
Technology-assisted Personalized Yoga for Better Health -- Challenges and Outlook
Adaptive Variance-Penalized Continual Learning with Fisher Regularization
Recurrent Transformer U-Net Surrogate for Flow Modeling and Data Assimilation in Subsurface Formations with Faults
The Impact of Artificial Intelligence on Human Thought
Detecting Hope, Hate, and Emotion in Arabic Textual Speech and Multi-modal Memes Using Large Language Models
Scalable FPGA Framework for Real-Time Denoising in High-Throughput Imaging: A DRAM-Optimized Pipeline using High-Level Synthesis
Transsion Multilingual Speech Recognition System for MLC-SLM 2025 Challenge
Non-Dissipative Graph Propagation for Non-Local Community Detection
The Rise of Generative AI for Metal-Organic Framework Design and Synthesis
Contextual Attention-Based Multimodal Fusion of LLM and CNN for Sentiment Analysis
Benchmarking GPT-5 for Zero-Shot Multimodal Medical Reasoning in Radiology and Radiation Oncology
Preference Models assume Proportional Hazards of Utilities
AVEX: What Matters for Animal Vocalization Encoding
Recent Advances in Transformer and Large Language Models for UAV Applications
When Does Language Transfer Help? Sequential Fine-Tuning for Cross-Lingual Euphemism Detection
A Survey of Idiom Datasets for Psycholinguistic and Computational Research
From Pixels to Graphs: Deep Graph-Level Anomaly Detection on Dermoscopic Images
Towards Understanding 3D Vision: the Role of Gaussian Curvature
Hallucination Detection and Mitigation in Scientific Text Simplification using Ensemble Approaches: DS@GT at CLEF 2025 SimpleText
LLM-Guided Planning and Summary-Based Scientific Text Simplification: DS@GT at CLEF 2025 SimpleText
FairTabGen: High-Fidelity and Fair Synthetic Health Data Generation from Limited Samples
An MLP Baseline for Handwriting Recognition Using Planar Curvature and Gradient Orientation

All 255