Papers

New on arXiv

Sun 30 Mar 2025

168 papers

Hyper-RAG: Combating LLM Hallucinations using Hypergraph-Driven Retrieval-Augmented GenerationRetrieval-augmented generation → Hallucination detection in RAG
VFlow: Discovering Optimal Agentic Workflows for Verilog GenerationLLM agents and tool use → Software engineering coding agents
A Hybrid Reinforcement Learning Framework for Hard Latency Constrained Resource SchedulingDeep reinforcement learning methods → RL for energy, networks and operations
CrossWordBench: Evaluating the Reasoning Capabilities of LLMs and LVLMs with Controllable Puzzle GenerationLLM reasoning → Multimodal reasoning +1
Protecting Creative Writing Copyright against AI Imitation via Implicit WatermarkingLLM safety and security → Watermarking generated content and models
Language-Guided Trajectory Traversal in Disentangled Stable Diffusion Latent Space for Factorized Medical Image GenerationDiffusion models → Medical imaging and segmentation
Leveraging Vision-Language Foundation Models to Reveal Hidden Image-Attribute Relationships in Medical ImagingMultimodal LLMs / vision-language models → Medical vision-language models
Exploring GPT-4 for Robotic Agent Strategy with Real-Time State Feedback and a Reactive Behaviour FrameworkLLM agents and tool use → Multimodal and embodied agents
GenVP: Generating Visual Puzzles with Contrastive Hierarchical VAEsLLM reasoning → Multimodal reasoning
DiT4SR: Taming Diffusion Transformer for Real-World Image Super-ResolutionDiffusion models → Inverse problems and image restoration
DASH: Detection and Assessment of Systematic Hallucinations of VLMsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
R900: Understanding the Cost-Effectiveness of Random Exploration from 900 Hours of Robotic Data CollectionOffline RL and imitation learning from data → Robot manipulation imitation learning
Enhancing Creative Generation on Stable Diffusion-based ModelsDiffusion models → Image generation, text-to-image and editing
BoundMatch: Boundary detection applied to semi-supervised segmentationKnowledge distillation → Detection and dense prediction distillation
RARE: Retrieval-Augmented Reasoning ModelingLLM reasoning → Knowledge- and tool-augmented reasoning +1
Re-Aligning Language to Visual Objects with an Agentic WorkflowLLM agents and tool use → Multimodal and embodied agents
Evolutionary Prompt Optimization Discovers Emergent Multimodal Reasoning Strategies in Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
Embedding Shift Dissection on CLIP: Effects of Augmentations on VLM's Representation LearningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP +1
Large Language and Reasoning Models are Shallow Disjunctive ReasonersLLM reasoning → Reasoning benchmarks and evaluation
Handling Delay in Real-Time Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action ModelVision-language-action models → VLA for autonomous driving +1
Reinforcement Learning-based Token Pruning in Vision Transformers: A Markov Game ApproachEfficient LLM inference and serving → Token pruning and merging for ViTs +1
Efficient Token Compression for Vision Transformer with Spatial Information PreservedEfficient LLM inference and serving → Token pruning and merging for ViTs
VideoGen-Eval: Agent-based System for Video Generation EvaluationLLM agents and tool use → Multimodal and embodied agents
Towards Trustworthy GUI Agents: A SurveyLLM agents and tool use → GUI and mobile agents
CoRanking: Collaborative Ranking with Small and Large Ranking AgentsLLM agents and tool use → Web, search, and research agents
A Multi-agent Onboarding Assistant based on Large Language Models, Retrieval Augmented Generation, and Chain-of-ThoughtLLM reasoning → Reasoning for agents, planning and code +2
An Analysis of Decoding Methods for LLM-based Agents for Faithful Multi-Hop Question AnsweringLLM agents and tool use → Web, search, and research agents
Scaling Auditory Cognition via Test-Time Compute in Audio Language ModelsLLM reasoning → Audio-language model reasoning
COSMIC: Clique-Oriented Semantic Multi-space Integration for Robust CLIP Test-Time AdaptationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
ToRL: Scaling Tool-Integrated RLLLM agents and tool use → Reinforcement learning for LLM agents
JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior SynchronizationDiffusion models → Audio, speech and music
FeRG-LLM : Feature Engineering by Reason Generation Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
VLIPP: Towards Physically Plausible Video Generation with Vision and Language Informed Physical PriorDiffusion models → Video generation
FastVAR: Linear Visual Autoregressive Modeling via Cached Token PruningEfficient LLM inference and serving → Fast autoregressive visual generation
Large Language Models Are Better Logical Fallacy Reasoners with Counterargument, Explanation, and Goal-Aware Prompt FormulationLLM reasoning → Reasoning benchmarks and evaluation
Mixture of RoutersLLM alignment / RLHF / preference optimisation → LLM preference optimization methods +1
DSPFusion: Image Fusion via Degradation and Semantic Dual-Prior GuidanceDiffusion models → Image generation, text-to-image and editing
A Survey of WebAgents: Towards Next-Generation AI Agents for Web Automation with Large Foundation ModelsLLM agents and tool use → Web, search, and research agents
From Panels to Prose: Generating Literary Narratives from ComicsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
TraceMark-LDM: Authenticatable Watermarking for Latent Diffusion Models via Binary-Guided RearrangementDiffusion models → Robustness, privacy and adversarial aspects +1
EagleVision: Object-level Attribute Multimodal LLM for Remote SensingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
A Multi-Agent Framework with Automated Decision Rule Optimization for Cross-Domain Misinformation DetectionLLM agents and tool use → Web, search, and research agents
AI Agents in Engineering Design: A Multi-Agent Framework for Aesthetic and Aerodynamic Car DesignLLM agents and tool use → Multimodal and embodied agents
SPIO: Ensemble and Selective Strategies via LLM-Based Multi-Agent Planning in Automated Data ScienceLLM reasoning → Reasoning for agents, planning and code +1
LaViC: Adapting Large Vision-Language Models to Visually-Aware Conversational RecommendationMultimodal LLMs / vision-language models → Document understanding and multimodal RAG +1
Reinforcement Learning for Active MatterDeep reinforcement learning methods → RL theory and sample complexity
SalesRLAgent: A Reinforcement Learning Approach for Real-Time Sales Conversion Prediction and OptimizationRetrieval-augmented generation → Agentic RAG, agents and memory +1
ReasonGrounder: LVLM-Guided Hierarchical Feature Splatting for Open-Vocabulary 3D Visual Grounding and ReasoningLLM reasoning → Spatial and embodied reasoning
Cocktail: Chunk-Adaptive Mixed-Precision Quantization for Long-Context LLM InferenceEfficient LLM inference and serving → KV cache quantization
PromptDistill: Query-based Selective Token Retention in Intermediate Layers for Efficient Large Language Model InferenceEfficient LLM inference and serving → KV cache optimization
Advanced Deep Learning and Large Language Models: Comprehensive Insights for Cancer Detection
Multi-Dimensional AGV Path Planning in 3D Warehouses Using Ant Colony Optimization and Advanced Neural Networks
Carbon Footprint Evaluation of Code Generation through LLM as a Service
Novel sparse PCA method via Runge Kutta numerical method(s) for face recognition
Artificial intelligence and democracy: Towards digital authoritarianism or a democratic upgrade?
Distill-C: Enhanced NL2SQL via Distilled Customization with LLMs
EAP4EMSIG -- Enhancing Event-Driven Microscopy for Microfluidic Single-Cell Analysis
Multi-Stakeholder Disaster Insights from Social Media Using Large Language Models
Measuring Online Hate on 4chan using Pre-trained Deep Learning Models
Dynamic hashtag recommendation in social media with trend shift detection and adaptation
Beyond the Reported Cutoff: Where Large Language Models Fall Short on Financial Knowledge
Imbalanced malware classification: an approach based on dynamic classifier selection
Quantum Methods for Managing Ambiguity in Natural Language Processing
Revisiting the Relationship between Adversarial and Clean Training: Why Clean Training Can Make Adversarial Training Better
ViT-Linearizer: Distilling Quadratic Knowledge into Linear-Time Vision Models
Improving Diseases Predictions Utilizing External Bio-Banks
Quantum Generative Models for Image Generation: Insights from MNIST and MedMNIST
A Constrained Multi-Agent Reinforcement Learning Approach to Autonomous Traffic Signal Control
Beyond Detection: Designing AI-Resilient Assessments with Automated Feedback Tool to Foster Critical Thinking
Simple Feedfoward Neural Networks are Almost All You Need for Time Series Forecasting
Graph-Eq: Discovering Mathematical Equations using Graph Generative Models
Interpretable Machine Learning in Physics: A Review
An Organizationally-Oriented Approach to Enhancing Explainability and Control in Multi-Agent Reinforcement Learning
Diffusion-Free Graph Generation with Next-Scale Prediction
Autonomous Learning with High-Dimensional Computing Architecture Similar to von Neumann's
Blurry-Edges: Photon-Limited Depth Estimation from Defocused Boundaries
Partial Transportability for Domain Generalization
Space of Data through the Lens of Multilevel Graph
Online Convex Optimization and Integral Quadratic Constraints: An automated approach to regret analysis
Multi-Objective Optimization and Hyperparameter Tuning With Desirability Functions
PhysPose: Refining 6D Object Poses with Physical Constraints
Multiview Image-Based Localization
The Impact of Code-switched Synthetic Data Quality is Task Dependent: Insights from MT and ASR
When LLM Therapists Become Salespeople: Evaluating Large Language Models for Ethical Motivational Interviewing
Bridging conformal prediction and scenario optimization
Addressing Model Overcomplexity in Drug-Drug Interaction Prediction With Molecular Fingerprints
NRC VAD Lexicon v2: Norms for Valence, Arousal, and Dominance for over 55k English Terms
Whisper-LM: Improving ASR Models with Language Models for Low-Resource Languages
Redundant feature screening method for human activity recognition based on attention purification mechanism
A Survey on Unlearnable Data
In-silico biological discovery with large perturbation models
BiPVL-Seg: Bidirectional Progressive Vision-Language Fusion with Global-Local Alignment for Medical Image Segmentation
ViLAaD: Enhancing "Attracting and Dispersing'' Source-Free Domain Adaptation with Vision-and-Language Model
Question-Aware Knowledge Graph Prompting for Enhancing Large Language Models
Optimal Invariant Bases for Atomistic Machine Learning
If an LLM Were a Character, Would It Know Its Own Story? Evaluating Lifelong Learning in LLMs
SCORE: Story Coherence and Retrieval Enhancement for AI Narratives
Buffer is All You Need: Defending Federated Learning against Backdoor Attacks under Non-iids via Buffering
ReferDINO-Plus: 2nd Solution for 4th PVUW MeViS Challenge at CVPR 2025

All 168