Papers

New on arXiv

Fri 28 Feb 2025

359 papers

SuperRAG: Beyond RAG with Layout-Aware Graph ModelingRetrieval-augmented generation → Multimodal RAG
Aligning Extraction and Generation for Robust Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval +1
AgroLLM: Connecting Farmers and Agricultural Practices through Large Language Models for Enhanced Knowledge Transfer and Practical ApplicationRetrieval-augmented generation → Time series and agricultural RAG
Attend or Perish: Benchmarking Attention in Algorithmic ReasoningLLM reasoning → Test-time compute and efficient thinking
UDora: A Unified Red Teaming Framework against LLM Agents by Dynamically Hijacking Their Own ReasoningLLM reasoning → Reasoning for agents, planning and code +2
CoSMoEs: Compact Sparse Mixture of ExpertsMixture-of-experts → Efficient MoE training and inference systems
Passage Query Methods for Retrieval and Reranking in Conversational AgentsLLM agents and tool use → Web, search, and research agents
Agentic AI Needs a Systems TheoryLLM reasoning → Reasoning for agents, planning and code +1
Jawaher: A Multidialectal Dataset of Arabic Proverbs for LLM BenchmarkingLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
The Learning Approach to GamesDeep reinforcement learning methods → RL for games and combinatorial optimization
SafeAuto: Knowledge-Enhanced Safe Autonomous Driving with Multimodal Foundation ModelsEnd-to-end autonomous driving → VLMs for autonomous driving
Quantifying First-Order Markov Violations in Noisy Reinforcement Learning: A Causal Discovery ApproachDeep reinforcement learning methods → Deep RL algorithms and representations
PRISM: High-Resolution & Precise Counterfactual Medical Image Generation using Language-guided Stable DiffusionDiffusion models → Medical imaging and segmentation
ProDapt: Proprioceptive Adaptation using Long-term Memory DiffusionDiffusion models → Diffusion and flow policies for robotics +1
Adaptive Reinforcement Learning for State Avoidance in Discrete Event SystemsDeep reinforcement learning methods → Deep RL algorithms and representations
Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking AttacksLLM safety and security → Jailbreaking
Steering Large Language Model Activations in Sparse SpacesMechanistic interpretability → Activation steering methods
Transforming Cyber Defense: Harnessing Agentic and Frontier AI for Proactive, Ethical Threat IntelligenceLLM agents and tool use → Agent threats, guardrails and governance
PreMind: Multi-Agent Video Understanding for Advanced Indexing of Presentation-style VideosLLM agents and tool use → Multimodal and embodied agents
Personalized Causal Graph Reasoning for LLMs: An Implementation for Dietary RecommendationsLLM reasoning → Clinical and biomedical applications
BixBench: a Comprehensive Benchmark for LLM-based Agents in Computational BiologyLLM agents and tool use → Medical and scientific domain agents
Rethinking LLM Bias Probing Using Lessons from the Social SciencesLLM reasoning → Reasoning benchmarks and evaluation
EdgeAIGuard: Agentic LLMs for Minor Protection in Digital SpacesLLM agents and tool use → Agent threats, guardrails and governance
InspireMusic: Integrating Super Resolution and Large Language Model for High-Fidelity Long-Form Music GenerationDiffusion models → Audio, speech and music
LLM Post-Training: A Deep Dive into Reasoning Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
Raccoon: Multi-stage Diffusion Training with Coarse-to-Fine Curating VideosDiffusion models → Video generation
Reasoning is Periodicity? Improving Large Language Models Through Effective Periodicity ModelingLLM reasoning → Reasoning benchmarks and evaluation
MIGE: Mutually Enhanced Multimodal Instruction-Based Image Generation and EditingDiffusion models → Image generation, text-to-image and editing
Does Generation Require Memorization? Creative Diffusion Models using Ambient DiffusionDiffusion models → Diffusion foundations and sampling
Adaptive Keyframe Sampling for Long Video UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs
ReaLJam: Real-Time Human-AI Music Jamming with Reinforcement Learning-Tuned TransformersDeep reinforcement learning methods → RL for robot locomotion and manipulation
PET Image Denoising via Text-Guided Diffusion: Integrating Anatomical Priors through Text PromptsDiffusion models → Medical imaging and segmentation
RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to ConcreteMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
A Method of Selective Attention for Reservoir Based AgentsDeep reinforcement learning methods → Deep RL algorithms and representations
Transformers Learn to Implement Multi-step Gradient Descent with Chain of ThoughtLLM reasoning → Prompting and chain-of-thought reasoning
ARIES: Autonomous Reasoning with LLMs on Interactive Thought Graph EnvironmentsLLM reasoning → Reasoning for agents, planning and code +1
Scalable Decision-Making in Stochastic Environments through Learned Temporal AbstractionOffline RL and imitation learning from data → Diffusion and flow policies for offline RL
Reducing Reward Dependence in RL Through Adaptive Confidence DiscountingDeep reinforcement learning methods → RL training of language and agent models
Multimodal Dreaming: A Global Workspace Approach to World Model-Based Reinforcement LearningWorld models → Latent dynamics models and model-based RL +1
Dynamically Local-Enhancement Planner for Large-Scale Autonomous DrivingEnd-to-end autonomous driving → Imitation-learning end-to-end planners
Generating patient cohorts from electronic health records using two-step retrieval-augmented text-to-SQL generationRetrieval-augmented generation → Medical and biomedical RAG
AuthSim: Towards Authentic and Effective Safety-critical Scenario Generation for Autonomous Driving TestsEnd-to-end autonomous driving → Adversarial scenarios and safety testing
PASemiQA: Plan-Assisted Agent for Question Answering on Semi-Structured Data with Text and Relational InformationRetrieval-augmented generation → RAG robustness and adaptive retrieval +1
Training-free and Adaptive Sparse Attention for Efficient Long Video GenerationDiffusion models → Video generation
Spatial Reasoning with Denoising ModelsLLM reasoning → Spatial and embodied reasoning
CODI: Compressing Chain-of-Thought into Continuous Space via Self-DistillationLLM reasoning → Prompting and chain-of-thought reasoning +1
FC-Attack: Jailbreaking Multimodal Large Language Models via Auto-Generated FlowchartsLLM safety and security → Vision-language and text-to-image safety
Robust Deterministic Policy Gradient for Disturbance Attenuation and Its Application to Quadrotor ControlDeep reinforcement learning methods → RL for robot navigation and UAV control
Reward Learning from Multiple Feedback TypesLLM agents and tool use → Reinforcement learning for LLM agents +1
Beyond Words: A Latent Memory Approach to Internal Reasoning in LLMsLLM reasoning → Reasoning benchmarks and evaluation
The RAG Paradox: A Black-Box Attack Exploiting Unintentional Vulnerabilities in Retrieval-Augmented Generation SystemsRetrieval-augmented generation → Privacy and security of RAG
Motion ReTouch: Motion Modification Using Four-Channel Bilateral ControlOffline RL and imitation learning from data → Robot manipulation imitation learning
TeleRAG: Efficient Retrieval-Augmented Generation Inference with Lookahead RetrievalRetrieval-augmented generation → RAG pipeline design and evaluation
Fine-Grained Knowledge Structuring and Retrieval for Visual Question AnsweringRetrieval-augmented generation → Multimodal RAG
Retrieval Augmented Generation for Topic Modeling in Organizational Research: An Introduction with Empirical DemonstrationRetrieval-augmented generation → Agentic RAG, agents and memory +1
Reward Dimension Reduction for Scalable Multi-Objective Reinforcement LearningDeep reinforcement learning methods → RL for games and combinatorial optimization
Optimality and Suboptimality of MPPI Control in Stochastic and Deterministic SettingsDeep reinforcement learning methods → RL for autonomous driving and traffic
Efficient Jailbreaking of Large Models by Freeze Training: Lower Layers Exhibit Greater Sensitivity to Harmful ContentLLM safety and security → Jailbreaking
Generative Uncertainty in Diffusion ModelsDiffusion models → Diffusion foundations and sampling
Everything, Everywhere, All at Once: Is Mechanistic Interpretability Identifiable?Mechanistic interpretability → Circuits and mechanistic analysis
DiffBrush:Just Painting the Art by Your HandsDiffusion models → Image generation, text-to-image and editing
DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous GraspingVision-language-action models → Human-video and latent-action pretraining
ProBench: Benchmarking Large Language Models in Competitive ProgrammingLLM reasoning → Reasoning for agents, planning and code
The Power of Personality: A Human Simulation Perspective to Investigate Large Language Model AgentsLLM agents and tool use → Social simulation and multi-agent debate
A Pilot Empirical Study on When and How to Use Knowledge Graphs as Retrieval Augmented GenerationRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
VLEER: Vision and Language Embeddings for Explainable Whole Slide Image RepresentationMultimodal LLMs / vision-language models → Medical vision-language models
Gradient Imbalance in Direct Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Reinforcement Learning with Curriculum-inspired Adaptive Direct Policy Guidance for Truck DispatchingDeep reinforcement learning methods → RL for autonomous driving and traffic
CoTMR: Chain-of-Thought Multi-Scale Reasoning for Training-Free Zero-Shot Composed Image RetrievalLLM reasoning → Multimodal reasoning
HAIC: Improving Human Action Understanding and Generation with Better Captions for Multi-modal Large Language ModelsMultimodal LLMs / vision-language models → Video understanding with MLLMs
MV-MATH: Evaluating Multimodal Math Reasoning in Multi-Visual ContextsLLM reasoning → Multimodal reasoning +1
Digital Player: Evaluating Large Language Models based Human-like Agent in GamesLLM agents and tool use → Reinforcement learning for LLM agents
Test-Time Alignment for Large Language Models via Textual Model Predictive ControlLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
CyLens: Towards Reinventing Cyber Threat Intelligence in the Paradigm of Agentic Large Language ModelsLLM agents and tool use → Agent threats, guardrails and governance
Chain-of-Thought Matters: Improving Long-Context Language Models with Reasoning Path SupervisionLLM reasoning → Prompting and chain-of-thought reasoning
MedHallTune: An Instruction-Tuning Benchmark for Mitigating Medical Hallucination in Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
Visual Attention Exploration in Vision-Based Mamba ModelsState-space sequence models (S4, Mamba) → Vision Mamba backbones
VRM: Knowledge Distillation via Virtual Relation MatchingKnowledge distillation → General knowledge distillation methods
Collective Reasoning Among LLMs: A Framework for Answer Validation Without Ground TruthLLM reasoning → Reasoning benchmarks and evaluation
The Rise of Darkness: Safety-Utility Trade-Offs in Role-Playing Dialogue AgentsLLM agents and tool use → Agent threats, guardrails and governance
Mitigating Hallucinations in Large Vision-Language Models by Adaptively Constraining Information FlowMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
Teach-to-Reason with Scoring: Self-Explainable Rationale-Driven Multi-Trait Essay ScoringLLM reasoning → Reasoning benchmarks and evaluation
Structured Preference Optimization for Vision-Language Long-Horizon Task PlanningLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
CADDreamer: CAD Object Generation from Single-view ImagesDiffusion models → 3D, point cloud and scene generation
Unlearning through Knowledge Overwriting: Reversible Federated Unlearning via Selective Sparse AdapterLLM safety and security → Federated unlearning and poisoning
Fuzzy Speculative Decoding for a Tunable Accuracy-Runtime TradeoffEfficient LLM inference and serving → Speculative decoding
WorldModelBench: Judging Video Generation Models As World ModelsWorld models → Video-generation world models and simulators
WiseMind: a knowledge-guided multi-agent framework for accurate and empathetic psychiatric diagnosisLLM agents and tool use → Medical and scientific domain agents
JAM: Controllable and Responsible Text Generation via Causal Reasoning and Latent Vector ManipulationLLM reasoning → Causal reasoning in LLMs
Diffusion Restoration Adapter for Real-World Image RestorationDiffusion models → Inverse problems and image restoration
Advancing AI-Powered Medical Image Synthesis: Insights from MedVQA-GI Challenge Using CLIP, Fine-Tuned Stable Diffusion, and Dream-Booth + LoRADiffusion models → Medical imaging and segmentation
Gungnir: Exploiting Stylistic Features in Images for Backdoor Attacks on Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
LexRAG: Benchmarking Retrieval-Augmented Generation in Multi-Turn Legal Consultation ConversationRetrieval-augmented generation → Legal and financial RAG
Subtask-Aware Visual Reward Learning from Segmented DemonstrationsDeep reinforcement learning methods → RL for robot locomotion and manipulation
Rectifying Belief Space via Unlearning to Harness LLMs' ReasoningLLM reasoning → Test-time compute and efficient thinking +1
PersonaBench: Evaluating AI Models on Understanding Personal Information through Accessing (Synthetic) Private User DataRetrieval-augmented generation → Privacy and security of RAG
Hybrid Retrieval for Hallucination Mitigation in Large Language Models: A Comparative Analysis
Towards properly implementing Theory of Mind in AI systems: An account of four misconceptions
Enhancing Explainability with Multimodal Context Representations for Smarter Robots
How Metacognitive Architectures Remember Their Own Thoughts: A Systematic Review

All 359