Papers

New on arXiv

Sun 23 Mar 2025

173 papers

ExpertRAG: Efficient RAG with Mixture of Experts -- Optimizing Context Retrieval for Adaptive LLM ResponsesRetrieval-augmented generation → RAG pipeline design and evaluation +1
Simulating Filter Bubble on Short-video Recommender System with Large Language Model AgentsLLM agents and tool use → Agentic recommender systems
Agentic Business Process Management: Practitioner Perspectives on Agent Governance in Business ProcessesLLM agents and tool use → Software engineering coding agents
Inverse Reinforcement Learning with Dynamic Reward Scaling for LLM AlignmentLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
A Novel Hat-Shaped Device-Cloud Collaborative Inference Framework for Large Language ModelsEfficient LLM inference and serving → Early exit and edge inference
FedSKD: Aggregation-free Model-heterogeneous Federated Learning via Multi-dimensional Similarity Knowledge Distillation for Medical Image ClassificationKnowledge distillation → Federated, robust and private distillation
CAE: Repurposing the Critic as an Explorer in Deep Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
CustomKD: Customizing Large Vision Foundation for Edge Model Improvement via Knowledge DistillationKnowledge distillation → General knowledge distillation methods
KEA: Keeping Exploration Alive by Proactively Coordinating Exploration StrategiesDeep reinforcement learning methods → Deep RL algorithms and representations
Adaptive Multi-Fidelity Reinforcement Learning for Variance Reduction in Engineering Design OptimizationDeep reinforcement learning methods → RL theory and sample complexity
ViVa: Video-Trained Value Functions for Guiding Online RL from Diverse DataDeep reinforcement learning methods → Deep RL algorithms and representations
FROG: Fair Removal on GraphsLLM safety and security → Graph unlearning
GINGER: Grounded Information Nugget-Based Generation of ResponsesRetrieval-augmented generation → RAG pipeline design and evaluation
Unmasking Deceptive Visuals: Benchmarking Multimodal Large Language Models on Misleading Chart Question AnsweringMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
Self-Attention Diffusion Models for Zero-Shot Biomedical Image Segmentation: Unlocking New Frontiers in Medical ImagingDiffusion models → Medical imaging and segmentation
MAO: Efficient Model-Agnostic Optimization of Prompt Tuning for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Adoption of Watermarking for Generative AI Systems in Practice and Implications under the new EU AI ActLLM safety and security → Watermarking generated content and models
LongDiff: Training-Free Long Video Generation in One GoDiffusion models → Video generation
LocDiff: Identifying Locations on Earth by Diffusing in the Hilbert SpaceDiffusion models → Inverse problems and image restoration
AGIR: Assessing 3D Gait Impairment with Reasoning based on LLMsLLM reasoning → Clinical and biomedical applications
TCFG: Tangential Damping Classifier-free GuidanceDiffusion models → Diffusion foundations and sampling
MLLM-For3D: Adapting Multimodal Large Language Model for 3D Reasoning SegmentationLLM reasoning → Spatial and embodied reasoning +1
MathAgent: Leveraging a Mixture-of-Math-Agent Framework for Real-World Multimodal Mathematical Error DetectionLLM reasoning → Mathematical reasoning +2
Mitigating Reward Over-Optimization in RLHF via Behavior-Supported RegularizationLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
GeoBenchX: Benchmarking LLMs in Agent Solving Multistep Geospatial TasksLLM agents and tool use → Multimodal and embodied agents
Detection of Somali-written Fake News and Toxic Messages on the Social Media Using Transformer-based Language ModelsLLM safety and security → Safety alignment, refusal and guardrails
Unraveling the Effects of Synthetic Data on End-to-End Autonomous DrivingWorld models → World models for autonomous driving +1
D2LoRA: Data-Driven LoRA Initialization for Low Resource TasksLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Unified Geometry and Color Compression Framework for Point Clouds via Generative Diffusion PriorsDiffusion models → 3D, point cloud and scene generation
A Multi-Model Adaptation of Speculative Decoding for ClassificationEfficient LLM inference and serving → Speculative decoding
Mind with Eyes: from Language Reasoning to Multimodal ReasoningLLM reasoning → Multimodal reasoning
Long Is More Important Than Difficult for Training Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking
Reinforcement Learning-based Self-adaptive Differential Evolution through Automated Landscape Feature LearningDeep reinforcement learning methods → RL for games and combinatorial optimization
Surrogate Learning in Meta-Black-Box Optimization: A Preliminary StudyDeep reinforcement learning methods → RL for games and combinatorial optimization
SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language PretrainingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Expanding the Boundaries of Vision Prior Knowledge in Multi-modal Large Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
OmnimatteZero: Fast Training-free Omnimatte with Pre-trained Video Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
Lost in Cultural Translation: Do LLMs Struggle with Math Across Cultural Contexts?LLM reasoning → Mathematical reasoning
Retrieval Augmented Generation and Understanding in Vision: A Survey and New OutlookRetrieval-augmented generation → Multimodal RAG
Vision-R1: Evolving Human-Free Alignment in Large Vision-Language Models via Vision-Guided Reinforcement LearningMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
Reason2Attack: Jailbreaking Text-to-Image Models via LLM ReasoningLLM reasoning → Reasoning for agents, planning and code +1
Optimizing Navigation And Chemical Application in Precision Agriculture With Deep Reinforcement Learning And Conditional Action TreeDeep reinforcement learning methods → RL for energy, networks and operations
Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational CapabilitiesLLM reasoning → Test-time compute and efficient thinking
Understanding the Effects of RLHF on the Quality and Detectability of LLM-Generated TextsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
Smoke and Mirrors: Jailbreaking LLM-based Code Generation via Implicit Malicious PromptsLLM safety and security → Jailbreaking
Selecting and Pruning: A Differentiable Causal Sequentialized State-Space Model for Two-View Correspondence LearningState-space sequence models (S4, Mamba) → Vision Mamba backbones
Experience Retrieval-Augmentation with Electronic Health Records Enables Accurate Discharge QARetrieval-augmented generation → Medical and biomedical RAG
STShield: Single-Token Sentinel for Real-Time Jailbreak Detection in Large Language ModelsLLM safety and security → Jailbreaking
Debiasing Multimodal Large Language Models via Noise-Aware Preference OptimizationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
WindowKV: Task-Adaptive Group-Wise KV Cache Window Selection for Efficient LLM InferenceEfficient LLM inference and serving → KV cache optimization
Guided Diffusion for the Extension of Machine Vision to Human Visual PerceptionDiffusion models → Diffusion for compression and wireless
GLADMamba: Unsupervised Graph-Level Anomaly Detection Powered by Selective State Space ModelState-space sequence models (S4, Mamba) → Time series forecasting with SSMs
Dynamic Topic Analysis in Academic Journals using Convex Non-negative Matrix Factorization Method
Recommendation System in Advertising and Streaming Media: Unsupervised Data Enhancement Sequence Suggestions
A Theoretical Framework for Graph-based Digital Twins for Supply Chain Management and Optimization
Learning to Interfere in Non-Orthogonal Multiple-Access Joint Source-Channel Coding
CLCR: Contrastive Learning-based Constraint Reordering for Efficient MILP Solving
Leveraging Large Language Models for Automated Causal Loop Diagram Generation: Enhancing System Dynamics Modeling through Curated Prompting Techniques
A Novel Two-Phase Cooperative Co-evolution Framework for Large-Scale Global Optimization with Complex Overlapping
Payload-Aware Intrusion Detection with CMAE and Large Language Models
"Whose Side Are You On?" Estimating Ideology of Political and News Content Using Large Language Models and Few-shot Demonstration Selection
Enhanced prediction of spine surgery outcomes using advanced machine learning techniques and oversampling methods
LLMs in the Classroom: Outcomes and Perceptions of Questions Written with the Aid of AI
HH4AI: A methodological Framework for AI Human Rights impact assessment under the EUAI ACT
SG-Tailor: Inter-Object Commonsense Relationship Reasoning for Scene Graph Manipulation
Balanced Direction from Multifarious Choices: Arithmetic Meta-Learning for Domain Generalization
SplitFrozen: Split Learning with Device-side Model Frozen for Fine-Tuning LLM on Heterogeneous Resource-Constrained Devices
LoRA Subtraction for Drift-Resistant Space in Exemplar-Free Continual Learning
A Physical and Mathematical Framework for the Semantic Theory of Evolution
Confronting Catastrophic Risk: The International Obligation to Regulate Artificial Intelligence
Generative Data Imputation for Sparse Learner Performance Data Using Generative Adversarial Imputation Networks
Threshold Crossings as Tail Events for Catastrophic AI Risk
ShED-HD: A Shannon Entropy Distribution Framework for Lightweight Hallucination Detection on Edge Devices
Collaborating with AI Agents: Field Experiments on Teamwork, Productivity, and Performance
Enhance GNNs with Reliable Confidence Estimation via Adversarial Calibration Learning
PG-SAM: Prior-Guided SAM with Medical for Multi-organ Segmentation
Mapping Hymns and Organizing Concepts in the Rigveda: Quantitatively Connecting the Vedic Suktas
DeLoRA: Decoupling Angles and Strength in Low-rank Adaptation
A Framework for Finding Local Saddle Points in Two-Player Zero-Sum Black-Box Games
MammAlps: A multi-view video behavior monitoring dataset of wild mammals in the Swiss Alps
Theory-to-Practice Gap for Neural Networks and Neural Operators
Adaptive Rank Allocation: Speeding Up Modern Transformers with RaNA Adapters
A Study on Neuro-Symbolic Artificial Intelligence: Healthcare Perspectives
LakotaBERT: A Transformer-based Model for Low Resource Lakota Language
SimMotionEdit: Text-Based Human Motion Editing with Motion Similarity Prediction
Iterative Multi-Agent Reinforcement Learning: A Novel Approach Toward Real-World Multi-Echelon Inventory Optimization
Shapley-Guided Utility Learning for Effective Graph Inference Data Valuation
Quantile-Based Randomized Kaczmarz for Corrupted Tensor Linear Systems
Exploring Energy Landscapes for Minimal Counterfactual Explanations: Applications in Cybersecurity and Beyond
Exploring Topic Trends in COVID-19 Research Literature using Non-Negative Matrix Factorization
Adaptive Physics-informed Neural Networks: A Survey
Causality-Aware Next Location Prediction Framework based on Human Mobility Stratification
Training A Neural Network For Partially Occluded Road Sign Identification In The Context Of Autonomous Vehicles
Enhancing Software Vulnerability Detection Using Code Property Graphs and Convolutional Neural Networks
Strategic Prompt Pricing for AIGC Services: A User-Centric Approach
Evaluating Negative Sampling Approaches for Neural Topic Models
SNRAware: Improved Deep Learning MRI Denoising with SNR Unit Training and G-factor Map Augmentation
Active Inference for Energy Control and Planning in Smart Buildings and Communities
DiffusionTalker: Efficient and Compact Speech-Driven 3D Talking Head via Personalizer-Guided Distillation
Decorum: A Language-Based Approach For Style-Conditioned Synthesis of Indoor 3D Scenes

All 173