Papers

New on arXiv

Fri 11 Apr 2025

269 papers

Near-Driven Autonomous Rover Navigation in Complex Environments: Extensions to Urban Search-and-Rescue and Industrial InspectionDeep reinforcement learning methods → RL for robot navigation and UAV control
The Other Side of the Coin: Exploring Fairness in Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
A Strategic Coordination Framework of Small LLMs Matches Large LLMs in Data SynthesisSynthetic data and self-improvement for LLMs → LLM synthetic data generation
SO-DETR: Leveraging Dual-Domain Features and Knowledge Distillation for Small Object DetectionKnowledge distillation → Detection and dense prediction distillation
Toward Super Agent System with Hybrid AI RoutersLLM agents and tool use → General LLM agent frameworks and benchmarks
CL-CoTNav: Closed-Loop Hierarchical Chain-of-Thought for Zero-Shot Object-Goal Navigation with Vision-Language ModelsLLM reasoning → Spatial and embodied reasoning +1
MCP Bridge: A Lightweight, LLM-Agnostic RESTful Proxy for Model Context Protocol ServersLLM agents and tool use → Agent threats, guardrails and governance
RouterKT: Mixture-of-Experts for Knowledge TracingMixture-of-experts → MoE large language models
AGENT: An Aerial Vehicle Generation and Design Tool Using Large Language ModelsLLM agents and tool use → Multimodal and embodied agents
Mixed Signals: Decoding VLMs' Reasoning and Underlying Bias in Vision-Language ConflictLLM reasoning → Multimodal reasoning +1
PACT: Pruning and Clustering-Based Token Reduction for Faster Visual Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
Investigating the Treacherous Turn in Deep Reinforcement LearningDeep reinforcement learning methods → Adversarial robustness and RL in finance
AgentRewardBench: Evaluating Automatic Evaluations of Web Agent TrajectoriesLLM agents and tool use → Web, search, and research agents
Long Context In-Context Compression by Getting to the Gist of GistingEfficient LLM inference and serving → Prompt and context compression
VectorLiteRAG: Latency-Aware and Fine-Grained Resource Partitioning for Efficient RAGRetrieval-augmented generation → RAG pipeline design and evaluation
Knowledge Graph-extended Retrieval Augmented Generation for Question AnsweringRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
RTLRepoCoder: Repository-Level RTL Code Completion through the Combination of Fine-Tuning and Retrieval AugmentationRetrieval-augmented generation → RAG for code
Mimic In-Context Learning for Multimodal TasksMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
SpecEE: Accelerating Large Language Model Inference with Speculative Early ExitingEfficient LLM inference and serving → Speculative decoding
X-Guard: Multilingual Guard Agent for Content ModerationLLM agents and tool use → Agent threats, guardrails and governance +1
AI University: An LLM-Powered Learning Assistant for Engineering---A Finite Element Method Case StudyRetrieval-augmented generation → Agentic RAG, agents and memory
Steering CLIP's vision transformer with sparse autoencodersMechanistic interpretability → Interpreting vision and multimodal models
Visual Chronicles: Using Multimodal LLMs to Analyze Massive Collections of ImagesMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
DocAgent: A Multi-Agent System for Automated Code Documentation GenerationLLM agents and tool use → Software engineering coding agents
EMO-X: Efficient Multi-Person Pose and Shape Estimation in One-StageState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
Offline Reinforcement Learning using Human-Aligned Reward Labeling for Autonomous Emergency Braking in Occluded Pedestrian CrossingOffline RL and imitation learning from data → Imitation and offline RL for driving
SWE-PolyBench: A multi-language benchmark for repository level evaluation of coding agentsLLM agents and tool use → Software engineering coding agents
SeaView: Software Engineering Agent Visual Interface for Enhanced WorkflowLLM agents and tool use → Software engineering coding agents
TP-RAG: Benchmarking Retrieval-Augmented Large Language Model Agents for Spatiotemporal-Aware Travel PlanningRetrieval-augmented generation → RAG for recommendation +1
Fast-Slow-Thinking: Complex Task Solving with Large Language ModelsLLM reasoning → Test-time compute and efficient thinking
Voice Interaction With Conversational AI Could Facilitate Thoughtful Reflection and Substantive Revision in WritingLLM reasoning → Reasoning benchmarks and evaluation
Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced ReasoningLLM reasoning → Test-time compute and efficient thinking +1
SafeFlow: Safe Robot Motion Planning with Flow Matching via Control Barrier FunctionsDiffusion models → Diffusion and flow policies for robotics
Reinforcement Learning-Driven Plant-Wide Refinery Planning Using Model DecompositionDeep reinforcement learning methods → RL for energy, networks and operations
Training-free Guidance in Text-to-Video Generation via Multimodal Planning and Structured Noise InitializationDiffusion models → Video generation
Do LLMs trust AI regulation? Emerging behaviour of game-theoretic LLM agentsLLM agents and tool use → Social simulation and multi-agent debate
Latent Diffusion Autoencoders: Toward Efficient and Meaningful Unsupervised Representation Learning in Medical ImagingDiffusion models → Medical imaging and segmentation
MooseAgent: A LLM Based Multi-agent Framework for Automating Moose SimulationLLM agents and tool use → Multimodal and embodied agents
Preserving Privacy Without Compromising Accuracy: Machine Unlearning for Handwritten Text RecognitionLLM safety and security → Machine unlearning
Neural Fidelity Calibration for Informative Sim-to-Real AdaptationDiffusion models → Diffusion and flow policies for robotics +1
ZipIR: Latent Pyramid Diffusion Transformer for High-Resolution Image RestorationDiffusion models → Inverse problems and image restoration
Playpen: An Environment for Exploring Learning Through Conversational InteractionLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
AstroLLaVA: towards the unification of astronomical data and natural languageMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Multimodal Knowledge Distillation for Egocentric Action Recognition Robust to Missing ModalitiesKnowledge distillation → Multimodal distillation
COP-GEN-Beta: Unified Generative Modelling of COPernicus Imagery ThumbnailsDiffusion models → Inverse problems and image restoration
Discriminator-Free Direct Preference Optimization for Video DiffusionDiffusion models → Video generation +1
Embodied Image Captioning: Self-supervised Learning Agents for Spatially Coherent Image DescriptionsLLM agents and tool use → Multimodal and embodied agents
Task Memory Engine (TME): Enhancing State Awareness for Multi-Step LLM Agent TasksLLM agents and tool use → Agent memory systems
Muon-Accelerated Attention Distillation for Real-Time Edge Synthesis via Optimized Latent DiffusionDiffusion models → Diffusion foundations and sampling
Speech Command + Speech Emotion: Exploring Emotional Speech Commands as a Compound and Playful ModalityLLM agents and tool use → Social simulation and multi-agent debate
Diffusion Models for Robotic Manipulation: A SurveyDiffusion models → Diffusion and flow policies for robotics
Beyond Self-Reports: Multi-Observer Agents for Personality Assessment in Large Language ModelsLLM agents and tool use → Social simulation and multi-agent debate
MixDiT: Accelerating Image Diffusion Transformer Inference with Mixed-Precision MX QuantizationDiffusion models → Diffusion foundations and sampling
MineWorld: a Real-Time and Open-Source Interactive World Model on MinecraftWorld models → Video-generation world models and simulators
PCA-RAG: Principal Component Analysis for Efficient Retrieval-Augmented GenerationRetrieval-augmented generation → Generation and context integration
LMM4LMM: Benchmarking and Evaluating Large-multimodal Image Generation with LMMsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Geometric Consistency Refinement for Single Image Novel View Synthesis via Test-Time Adaptation of Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
EasyGenNet: An Efficient Framework for Audio-Driven Gesture Video Generation Based on Diffusion ModelDiffusion models → Audio, speech and music
SortBench: Benchmarking LLMs based on their ability to sort listsLLM reasoning → Reasoning benchmarks and evaluation
Generative AI for Film Creation: A Survey of Recent AdvancesDiffusion models → Image generation, text-to-image and editing
DreamFuse: Adaptive Image Fusion with Diffusion TransformerDiffusion models → Image generation, text-to-image and editing
Palmprint De-Identification Using Diffusion Model for High-Quality and Diverse SynthesisDiffusion models → Robustness, privacy and adversarial aspects
Evaluating the Bias in LLMs for Surveying Opinion and Decision Making in HealthcareLLM agents and tool use → Social simulation and multi-agent debate
CoProSketch: Controllable and Progressive Sketch Generation with Diffusion ModelDiffusion models → Image generation, text-to-image and editing
RAG-VR: Leveraging Retrieval-Augmented Generation for 3D Question Answering in VR EnvironmentsRetrieval-augmented generation → Multimodal RAG
Understanding the Impact of Data Domain Extraction on Synthetic Data PrivacyLLM safety and security → Membership inference attacks
Knowledge Distillation for Underwater Feature Extraction and Matching via GAN-synthesized ImagesKnowledge distillation → Detection and dense prediction distillation
Millions of States: Designing a Scalable MoE Architecture with RWKV-7 Meta-learnerMixture-of-experts → MoE large language models
Spectral Normalization for Lipschitz-Constrained Policies on Learning Humanoid LocomotionDeep reinforcement learning methods → RL for robot locomotion and manipulation
Jupiter: Fast and Resource-Efficient Collaborative Inference of Generative LLMs on Edge DevicesEfficient LLM inference and serving → Early exit and edge inference
Out of Style: RAG's Fragility to Linguistic VariationRetrieval-augmented generation → RAG robustness and adaptive retrieval
Optimizing Power Grid Topologies with Reinforcement Learning: A Survey of Methods and ChallengesDeep reinforcement learning methods → RL for energy, networks and operations
SAEs Can Improve Unlearning: Dynamic Sparse Autoencoder Guardrails for Precision Unlearning in LLMsLLM safety and security → Machine unlearning +1
TokenMotion: Decoupled Motion Control via Token Disentanglement for Human-centric Video GenerationDiffusion models → Video generation
Follow the STARs: Dynamic ω-Regular Shielding of Learned Policies
Low-Bit Integerization of Vision Transformers using Operand Reordering for Efficient Hardware
Evaluation and Incident Prevention in an Enterprise AI Assistant
Modeling the quantum-like dynamics of human reliability ratings in Human-AI interactions by interaction dependent Hamiltonians
LLMTaxo: Leveraging Large Language Models for Constructing Taxonomy of Factual Claims from Social Media
Cross-Document Cross-Lingual NLI via RST-Enhanced Graph Fusion and Interpretability Prediction
High Dynamic Range Modulo Imaging for Robust Object Detection in Autonomous Driving
Do Segmentation Models Understand Vascular Structure? A Blob-Based XAI Framework
Remote Sensing Based Crop Health Classification Using NDVI and Fully Connected Neural Networks
Integrating Emotion Distribution Networks and Textual Message Analysis for X User Emotional State Classification
MSCCL++: Rethinking GPU Communication Abstractions for AI Inference
Learning in Structured Stackelberg Games
ReCA: A Parametric ReLU Composite Activation Function
Learning from Elders: Making an LLM-powered Chatbot for Retirement Communities more Accessible through User-centered Design
Adaptive Additive Parameter Updates of Vision Transformers for Few-Shot Continual Learning
Perfect Clustering in Nonuniform Hypergraphs
On Large-scale Evaluation of Embedding Models for Knowledge Graph Completion
Bidirectional Linear Recurrent Models for Sequence-Level Multisource Fusion
A Fully Automated Pipeline for Conversational Discourse Annotation: Tree Scheme Generation and Labeling with Large Language Models
MotionDreamer: One-to-Many Motion Synthesis with Localized Generative Masked Transformer
Generating Planning Feedback for Open-Ended Programming Exercises with LLMs
Large Language Model Empowered Recommendation Meets All-domain Continual Pre-Training
Forecasting Cryptocurrency Prices using Contextual ES-adRNN with Exogenous Variables
Combining Forecasts using Meta-Learning: A Comparative Study for Complex Seasonality
Rethinking Few-Shot Image Fusion: Granular Ball Priors Enable General-Purpose Deep Fusion
A convergence law for continuous logic and continuous structures with finite domains

All 269