Papers

New on arXiv

Tue 15 Apr 2025

328 papers

Nemotron-CrossThink: Scaling Self-Learning beyond Math ReasoningLLM reasoning → Reinforcement learning for reasoning
ViMo: A Generative Visual GUI World Model for App AgentsWorld models → World model security and GUI agents
On-Device Watermarking: A Socio-Technical Imperative For Authenticity In The Age of Generative AILLM safety and security → Watermarking generated content and models
X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
CEE: An Inference-Time Jailbreak Defense for Embodied Intelligence via Subspace Concept RotationLLM safety and security → Prompt injection and agent security
WaterFlow: Learning Fast & Robust Watermarks using Stable DiffusionDiffusion models → Robustness, privacy and adversarial aspects +1
Prototype-Guided Diffusion for Digital Pathology: Achieving Foundation Model Performance with Minimal Clinical DataDiffusion models → Medical imaging and segmentation
Assessment of Evolving Large Language Models in Upper Secondary MathematicsLLM reasoning → Mathematical reasoning
CRAB: A Benchmark for Evaluating Curation of Retrieval-Augmented LLMs in BiomedicineRetrieval-augmented generation → Medical and biomedical RAG
Co-STAR: Collaborative Curriculum Self-Training with Adaptive Regularization for Source-Free Video Domain AdaptationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP +1
70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float (DFloat11)Diffusion models → Diffusion foundations and sampling
Achieving Tighter Finite-Time Rates for Heterogeneous Federated Stochastic Approximation under Markovian SamplingDeep reinforcement learning methods → RL for energy, networks and operations
Dueling Deep Reinforcement Learning for Financial Time SeriesDeep reinforcement learning methods → Adversarial robustness and RL in finance
GraphicBench: A Planning Benchmark for Graphic Design with Language AgentsLLM agents and tool use → Multimodal and embodied agents
NodeRAG: Structuring Graph-based RAG with Heterogeneous NodesRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
REAL: Benchmarking Autonomous Agents on Deterministic Simulations of Real WebsitesLLM agents and tool use → Web, search, and research agents
ReTool: Reinforcement Learning for Strategic Tool Use in LLMsLLM reasoning → Reasoning for agents, planning and code +1
LANGTRAJ: Diffusion Model and Dataset for Language-Conditioned Trajectory SimulationDiffusion models → Diffusion and flow policies for robotics
Enhancing Autonomous Driving Systems with On-Board Deployed Large Language ModelsEnd-to-end autonomous driving → Large language models for driving
Position Paper: Rethinking Privacy in RL for Sequential Decision-making in the Age of LLMsLLM reasoning → Reasoning for agents, planning and code
PATFinger: Prompt-Adapted Transferable Fingerprinting against Unauthorized Multimodal Dataset UsageMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
Cross-cultural Deployment of Autonomous Vehicles Using Data-light Inverse Reinforcement LearningEnd-to-end autonomous driving → Reinforcement learning for driving +2
Aligning Generative Denoising with Discriminative Objectives Unleashes Diffusion for Visual PerceptionDiffusion models → Image generation, text-to-image and editing
DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing ReasoningLLM reasoning → Reinforcement learning for reasoning
A Clean Slate for Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
Diffusion Distillation With Direct Preference Optimization For Efficient 3D LiDAR Scene CompletionWorld models → World modeling from LiDAR generation +1
Mamba-Based Ensemble learning for White Blood Cell ClassificationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
NormalCrafter: Learning Temporally Consistent Normals from Video Diffusion PriorsDiffusion models → 3D, point cloud and scene generation
A Dual-Space Framework for General Knowledge Distillation of Large Language ModelsKnowledge distillation → Knowledge distillation for LLMs
ADT: Tuning Diffusion Models with Adversarial SupervisionDiffusion models → Diffusion foundations and sampling
Embodied World Models Emerge from Navigational Task in Open-Ended EnvironmentsWorld models → World models for navigation +1
Measures of Variability for Risk-averse Policy GradientDeep reinforcement learning methods → RL theory and sample complexity
From Gaze to Insight: Bridging Human Visual Attention and Vision Language Model Explanation for Weakly-Supervised Medical Image SegmentationMultimodal LLMs / vision-language models → Medical vision-language models
Offline Learning and Forgetting for Reasoning with Large Language ModelsLLM reasoning → Test-time compute and efficient thinking
DataSentinel: A Game-Theoretic Detection of Prompt Injection AttacksLLM safety and security → Prompt injection and agent security
Kimina-Prover Preview: Towards Large Formal Reasoning Models with Reinforcement LearningLLM reasoning → Mathematical reasoning
A Minimalist Approach to LLM Reasoning: from Rejection Sampling to ReinforceLLM reasoning → Reinforcement learning for reasoning
REWARD CONSISTENCY: Improving Multi-Objective Alignment from a Data-Centric PerspectiveLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Learning to Be A Doctor: Searching for Effective Medical Agent ArchitecturesLLM agents and tool use → Medical and scientific domain agents
Autoregressive Distillation of Diffusion TransformersDiffusion models → Diffusion foundations and sampling
UniAnimate-DiT: Human Image Animation with Large-Scale Video Diffusion TransformerDiffusion models → Video generation
The Obvious Invisible Threat: LLM-Powered GUI Agents' Vulnerability to Fine-Print InjectionsLLM agents and tool use → Agent threats, guardrails and governance
UI-E2I-Synth: Advancing GUI Grounding with Large-Scale Instruction SynthesisMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
Next-Future: Sample-Efficient Policy Learning for Robotic-Arm TasksDeep reinforcement learning methods → RL for robot locomotion and manipulation
Towards Automated Safety Requirements Derivation Using Agent-based RAGRetrieval-augmented generation → Multimodal RAG +1
Nondeterministic Polynomial-time Problem Challenge: An Ever-Scaling Reasoning Benchmark for LLMsLLM reasoning → Reasoning benchmarks and evaluation
Efficient Distributed Retrieval-Augmented Generation for Enhancing Language Model PerformanceRetrieval-augmented generation → RAG pipeline design and evaluation
R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt TuningMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
Enhancing multimodal analogical reasoning with Logic Augmented GenerationLLM reasoning → Reasoning benchmarks and evaluation
Benchmarking Next-Generation Reasoning-Focused Large Language Models in Ophthalmology: A Head-to-Head Evaluation on 5,888 ItemsLLM reasoning → Clinical and biomedical applications
Exploring Backdoor Attack and Defense for LLM-empowered RecommendationsLLM safety and security → Backdoor and data poisoning attacks
Bypassing LLM Guardrails: An Empirical Analysis of Evasion Attacks against Prompt Injection and Jailbreak Detection SystemsLLM safety and security → Jailbreaking
SAR-to-RGB Translation with Latent Diffusion for Earth ObservationDiffusion models → Inverse problems and image restoration
Exploring Student Behaviors and Motivations using AI TAs with Optional GuardrailsLLM safety and security → Safety alignment, refusal and guardrails
Taming Consistency Distillation for Accelerated Human Image AnimationDiffusion models → Video generation
BrickSmart: Leveraging Generative AI to Support Children's Spatial Language Learning in Family Block PlayLLM reasoning → Spatial and embodied reasoning
Revealing Human Attention Patterns from Gameplay Analysis for Reinforcement LearningDeep reinforcement learning methods → Interpretable and logic-guided RL
Agent-Q: Fine-Tuning Large Language Models for Quantum Circuit Generation and OptimizationLLM agents and tool use → Medical and scientific domain agents
Benchmarking Vision Language Models on German Factual DataMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Token-Level Constraint Boundary Search for Jailbreaking Text-to-Image ModelsLLM safety and security → Vision-language and text-to-image safety
Consensus Entropy: Harnessing Multi-VLM Agreement for Self-Verifying and Self-Improving OCRMultimodal LLMs / vision-language models → Document understanding and multimodal RAG +1
DeepMLF: Multimodal language model with learnable tokens for deep fusion in sentiment analysisMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Efficient Remote Sensing Change Detection with Change State Space ModelsState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation ModelsDeep reinforcement learning methods → Deep RL algorithms and representations
LazyReview A Dataset for Uncovering Lazy Thinking in NLP Peer ReviewsLLM reasoning → Knowledge- and tool-augmented reasoning
QAVA: Query-Agnostic Visual Attack to Large Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
Defending Against Frequency-Based Attacks with Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
A PyTorch-Compatible Spike Encoding Framework for Energy-Efficient Neuromorphic ApplicationsDeep reinforcement learning methods → Spiking and neuromorphic RL
AnimeDL-2M: Million-Scale AI-Generated Anime Image Detection and Localization in Diffusion EraDiffusion models → Image generation, text-to-image and editing
MMC: Iterative Refinement of VLM Reasoning via MCTS-based Multimodal CritiqueMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Dynamic Compressing Prompts for Efficient Inference of Large Language ModelsEfficient LLM inference and serving → Prompt and context compression
ReZero: Enhancing LLM search ability by trying one-more-timeRetrieval-augmented generation → Agentic RAG, agents and memory
Exploring the Role of Knowledge Graph-Based RAG in Japanese Medical Question Answering with Small-Scale LLMsRetrieval-augmented generation → Medical and biomedical RAG
An Efficient and Mixed Heterogeneous Model for Image RestorationState-space sequence models (S4, Mamba) → Mamba for image restoration
Evaluating Trust in AI, Human, and Co-produced Feedback Among Undergraduate StudentsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear TransformersLLM safety and security → Machine unlearning
Adaptive Human-Agent Teaming: A Review of Empirical Studies from the Process Dynamics PerspectiveLLM agents and tool use → General LLM agent frameworks and benchmarks
InterAnimate: Taming Region-aware Diffusion Model for Realistic Human Interaction AnimationDiffusion models → Video generation
Efficient Reasoning Models: A SurveyLLM reasoning → Test-time compute and efficient thinking
ARise: Towards Knowledge-Augmented Reasoning via Risk-Adaptive SearchLLM reasoning → Knowledge- and tool-augmented reasoning
Exploring Persona-dependent LLM Alignment for the Moral Machine ExperimentLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
PuzzleBench: A Fully Dynamic Evaluation Framework for Large Multimodal Models on Puzzle SolvingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Bringing together invertible UNets with invertible attention modules for memory-efficient diffusion modelsDiffusion models → Medical imaging and segmentation
Can Vision-Language Models Understand and Interpret Dynamic Gestures from Pedestrians? Pilot Datasets and Exploration Towards Instructive Nonverbal Commands for Cooperative Autonomous VehiclesMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
Understanding the theoretical properties of projected Bellman equation, linear Q-learning, and approximate value iterationDeep reinforcement learning methods → RL theory and sample complexity
Ai2 Scholar QA: Organized Literature Synthesis with AttributionRetrieval-augmented generation → Agentic RAG, agents and memory
LVLM_CSP: Accelerating Large Vision Language Models via Clustering, Scattering, and Pruning for Reasoning SegmentationLLM reasoning → Multimodal reasoning +2
PT-Mark: Invisible Watermarking for Text-to-image Diffusion Models via Semantic-aware Pivotal TuningDiffusion models → Robustness, privacy and adversarial aspects +1
Enhancing Features in Long-tailed Data Using Large Vision ModelMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Rethinking Theory of Mind Benchmarks for LLMs: Towards A User-Centered PerspectiveLLM reasoning → Reasoning benchmarks and evaluation
Hallucination-Aware Generative Pretrained Transformer for Cooperative Aerial Mobility ControlDeep reinforcement learning methods → RL for robot navigation and UAV control
LayoutCoT: Unleashing the Deep Reasoning Potential of Large Language Models for Layout GenerationLLM reasoning → Spatial and embodied reasoning
OmniVDiff: Omni Controllable Video Diffusion for Generation and UnderstandingDiffusion models → Video generation
Power-scaled Bayesian Inference with Score-based Generative ModelsDiffusion models → Inverse problems and image restoration
Visual Language Models show widespread visual deficits on neuropsychological testsLLM reasoning → Multimodal reasoning +1
High hopes for "Deep Medicine"? AI, economics, and the future of care
A Simulator Dataset to Support the Study of Impaired Driving
Bridging Equilibrium and Kinetics Prediction with a Data-Weighted Neural Network Model of Methane Steam Reforming
Rethinking Technological Readiness in the Era of AI Uncertainty
Recommending Clinical Trials for Online Patient Cases using Artificial Intelligence

All 328