Papers

New on arXiv

Thu 17 Jul 2025

297 papers

LLM Agent-Based Simulation of Student Activities and Mental Health Using Smartphone Sensing DataLLM agents and tool use → Medical and scientific domain agents
Generative AI Models for Learning Flow Maps of Stochastic Dynamical Systems in Bounded DomainsDiffusion models → Diffusion foundations and sampling
Why Braking? Scenario Extraction and Reasoning Utilizing LLMLLM reasoning → Chain-of-thought reasoning for driving
Learning to summarize user information for personalized reinforcement learning from human feedbackLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment +1
Apple Intelligence Foundation Language Models: Tech Report 2025Mixture-of-experts → Efficient MoE training and inference systems +1
LoRA-Loop: Closing the Synthetic Replay Cycle for Continual VLM LearningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP +1
GraphTrafficGPT: Enhancing Traffic Management Through Graph-Based AI Agent CoordinationLLM agents and tool use → Multimodal and embodied agents
Model-free Reinforcement Learning for Model-based Control: Towards Safe, Interpretable and Sample-efficient AgentsDeep reinforcement learning methods → Deep RL algorithms and representations
Paper Summary Attack: Jailbreaking LLMs through LLM Safety PapersLLM safety and security → Jailbreaking
LightAutoDS-Tab: Multi-AutoML Agentic System for Tabular DataLLM agents and tool use → Web, search, and research agents
Causal Language Control in Multilingual Transformers via Sparse Feature SteeringMechanistic interpretability → SAE features and their applications
IConMark: Robust Interpretable Concept-Based Watermark For AI ImagesLLM safety and security → Watermarking generated content and models
COREVQA: A Crowd Observation and Reasoning Entailment Visual Question Answering BenchmarkLLM reasoning → Multimodal reasoning +1
AortaDiff: Volume-Guided Conditional Diffusion Models for Multi-Branch Aortic Surface GenerationDiffusion models → Medical imaging and segmentation
Hierarchical Rectified Flow Matching with Mini-Batch CouplingsDiffusion models → Flow matching, time series and science
VisionThink: Smart and Efficient Vision Language Model via Reinforcement LearningLLM reasoning → Multimodal reasoning +1
Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
Taming Diffusion Transformer for Efficient Mobile Video Generation in SecondsDiffusion models → Video generation
Latent Policy Steering with Embodiment-Agnostic Pretrained World ModelsWorld models → Embodied and robot world models
The Imitation Game: Turing Machine Imitator is Length Generalizable ReasonerLLM reasoning → Prompting and chain-of-thought reasoning
Revisiting Reliability in the Reasoning-based Pose Estimation BenchmarkLLM reasoning → Spatial and embodied reasoning +1
Evaluating Reinforcement Learning Algorithms for Navigation in Simulated Robotic Quadrupeds: A Comparative Study Inspired by Guide Dog BehaviourDeep reinforcement learning methods → RL for robot locomotion and manipulation
QuestA: Expanding Reasoning Capacity in LLMs via Question AugmentationLLM reasoning → Reinforcement learning for reasoning
Automating Steering for Safe Multimodal Large Language ModelsLLM reasoning → Reasoning for agents, planning and code +1
Multilingual LLMs Are Not Multilingual Thinkers: Evidence from Hindi Analogy EvaluationLLM reasoning → Reasoning benchmarks and evaluation
Enhancing Cross-task Transfer of Large Language Models via Activation SteeringMechanistic interpretability → Activation steering methods
VITA: Vision-to-Action Flow Matching PolicyDiffusion models → Diffusion and flow policies for robotics
GEMMAS: Graph-based Evaluation Metrics for Multi Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
Spectral Bellman Method: Unifying Representation and Exploration in RLDeep reinforcement learning methods → RL theory and sample complexity
Black Box Deployed -- Functional Criteria for Artificial Moral Agents in the LLM EraLLM agents and tool use → General LLM agent frameworks and benchmarks
Aligning Humans and Robots via Reinforcement Learning from Implicit Human FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
Prompt Injection 2.0: Hybrid AI ThreatsLLM safety and security → Prompt injection and agent security
Orbis: Overcoming Challenges of Long-Horizon Prediction in Driving World ModelsWorld models → World models for autonomous driving +1
Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and OpportunitiesLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
SE-VLN: A Self-Evolving Vision-Language Navigation Framework Based on Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
fastWDM3D: Fast and Accurate 3D Healthy Tissue InpaintingDiffusion models → Medical imaging and segmentation
From Roots to Rewards: Dynamic Tree Reasoning with Reinforcement LearningLLM reasoning → Knowledge- and tool-augmented reasoning
R^2MoE: Redundancy-Removal Mixture of Experts for Lifelong Concept LearningMixture-of-experts → Mixture of LoRA experts
Uncertainty-Aware Cross-Modal Knowledge Distillation with Prototype Learning for Multimodal Brain-Computer InterfacesKnowledge distillation → Distillation for medical imaging
GLAD: Generalizable Tuning for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
ZipMPC: Compressed Context-Dependent MPC Cost via Imitation LearningOffline RL and imitation learning from data → Imitation and offline RL for driving
DiffOSeg: Omni Medical Image Segmentation via Multi-Expert Collaboration Diffusion ModelDiffusion models → Medical imaging and segmentation
Label-Consistent Dataset Distillation with Detector-Guided RefinementDiffusion models → Diffusion foundations and sampling
MAD-Spear: A Conformity-Driven Prompt Injection Attack on Multi-Agent Debate SystemsLLM agents and tool use → Social simulation and multi-agent debate +1
Resurrect Mask AutoRegressive Modeling for Efficient and Scalable Image GenerationEfficient LLM inference and serving → Fast autoregressive visual generation
Rethinking the Embodied Gap in Vision-and-Language Navigation: A Holistic Study of Physical and Visual DisparitiesLLM reasoning → Spatial and embodied reasoning
Teach Old SAEs New Domain Tricks with BoostingMechanistic interpretability → SAE features and their applications
From Variability To Accuracy: Conditional Bernoulli Diffusion Models with Consensus-Driven Correction for Thin Structure SegmentationDiffusion models → Medical imaging and segmentation
Non-differentiable Reward Optimization for Diffusion-based Autonomous Motion PlanningDiffusion models → Diffusion and flow policies for robotics
RGB Pre-Training Enhanced Unobservable Feature Latent Diffusion Model for Spectral ReconstructionDiffusion models → Inverse problems and image restoration
FantasyPortrait: Enhancing Multi-Character Portrait Animation with Expression-Augmented Diffusion TransformersDiffusion models → Audio, speech and music
LoViC: Efficient Long Video Generation with Context CompressionDiffusion models → Video generation +1
Insights into a radiology-specialised multimodal large language model with sparse autoencodersMultimodal LLMs / vision-language models → Medical vision-language models +1
Probabilistic Soundness Guarantees in LLM Reasoning ChainsLLM reasoning → Test-time compute and efficient thinking
Analysis of Image-and-Text Uncertainty Propagation in Multimodal Large Language Models with Cardiac MR-Based ApplicationsMultimodal LLMs / vision-language models → Medical vision-language models
DMQ: Dissecting Outliers of Diffusion Models for Post-Training QuantizationDiffusion models → Diffusion foundations and sampling
Improving DAPO from a Mixed-Policy PerspectiveDeep reinforcement learning methods → RL theory and sample complexity
Vidar: Embodied Video Diffusion Model for Generalist ManipulationDiffusion models → Diffusion and flow policies for robotics
VAR-MATH: Probing True Mathematical Reasoning in LLMS via Symbolic Multi-Instance BenchmarksLLM reasoning → Mathematical reasoning
Autonomous Resource Management in Microservice Systems via Reinforcement LearningDeep reinforcement learning methods → RL for energy, networks and operations
Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)Offline RL and imitation learning from data → Imitation learning methods +1
Machine-Readable Ads: Accessibility and Trust Patterns for AI Web Agents interacting with Online AdvertisementsLLM agents and tool use → Web, search, and research agents
Bridging the Gap: Leveraging Retrieval-Augmented Generation to Better Understand Public Concerns about VaccinesRetrieval-augmented generation → Medical and biomedical RAG
Assessing Adaptive World Models in Machines with Novel GamesWorld models → World models for language agents
MCoT-RE: Multi-Faceted Chain-of-Thought and Re-Ranking for Training-Free Zero-Shot Composed Image RetrievalLLM reasoning → Multimodal reasoning
From Novelty to Imitation: Self-Distilled Rewards for Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
MCPEval: Automatic MCP-based Deep Evaluation for AI Agent ModelsLLM agents and tool use → Tool learning and function calling
FLDmamba: Integrating Fourier and Laplace Transform Decomposition with Mamba for Enhanced Time Series PredictionState-space sequence models (S4, Mamba) → Time series forecasting with SSMs
Local Representative Token Guided Merging for Text-to-Image GenerationDiffusion models → Image generation, text-to-image and editing +1
World Model-Based End-to-End Scene Generation for Accident Anticipation in Autonomous DrivingWorld models → World models for autonomous driving +1
Think-Before-Draw: Decomposing Emotion Semantics & Fine-Grained Controllable Expressive Talking Head GenerationLLM reasoning → Audio-language model reasoning +1
Unified Medical Image Segmentation with State Space Modeling SnakeState-space sequence models (S4, Mamba) → Mamba for medical image analysis
Logit Arithmetic Elicits Long Reasoning Capabilities Without TrainingLLM reasoning → Test-time compute and efficient thinking +1
osmAG-LLM: Zero-Shot Open-Vocabulary Object Navigation via Semantic Maps and Large Language Models ReasoningLLM reasoning → Spatial and embodied reasoning
TransEvalnia: Reasoning-based Evaluation and Ranking of TranslationsLLM reasoning → Reasoning benchmarks and evaluation
Pixel Perfect MegaMed: A Megapixel-Scale Vision-Language Foundation Model for Generating High Resolution Medical ImagesMultimodal LLMs / vision-language models → Medical vision-language models
AnnoSense: A Framework for Physiological Emotion Data Collection in Everyday Settings for AI
Pre-, In-, and Post-Processing Class Imbalance Mitigation Techniques for Failure Detection in Optical Networks
Failure Risk Prediction in a MOOC: A Multivariate Time Series Analysis Approach
A Comprehensive Review on Harnessing Large Language Models to Overcome Recommender System Challenges
Enhancing Spatiotemporal Networks with xLSTM: A Scalar LSTM Approach for Cellular Traffic Forecasting
Advancing Mental Disorder Detection: A Comparative Evaluation of Transformer and LSTM Architectures on Social Media
Beyond 9-to-5: A Generative Model for Augmenting Mobility Data of Underrepresented Shift Workers
PolyServe: Efficient Multi-SLO Serving at Scale
Enhancing Quantization-Aware Training on Edge Devices via Relative Entropy Coreset Selection and Cascaded Layer Correction
Salience Adjustment for Context-Based Emotion Recognition
Out-of-Distribution Generalization in the ARC-AGI Domain: Comparing Execution-Guided Neural Program Synthesis and Test-Time Fine-Tuning
Re-evaluating Short- and Long-Term Trend Factors in CTA Replication: A Bayesian Graphical Approach
Differential Multimodal Transformers
Culling Misinformation from Gen AI: Toward Ethical Curation and Refinement
Promptomatix: An Automatic Prompt Optimization Framework for Large Language Models
HuggingGraph: Understanding the Supply Chain of LLM Ecosystem
CCL-XCoT: An Efficient Cross-Lingual Knowledge Transfer Method for Mitigating Hallucination Generation
Language Models Change Facts Based on the Way You Talk
U-DREAM: Unsupervised Dereverberation guided by a Reverberation Model
Mining Voter Behaviour and Confidence: A Rule-Based Analysis of the 2022 U.S. Elections
Beyond Architectures: Evaluating the Role of Contextual Embeddings in Detecting Bipolar Disorder on Social Media
Intent-Based Network for RAN Management with Large Language Models
A Collaborative Framework Integrating Large Language Model and Chemical Fragment Space: Mutual Inspiration for Lead Design
Change of Thought: Adaptive Test-Time Computation

All 297