Papers

New on arXiv

Sun 10 Aug 2025

174 papers

An Embodied AR Navigation Agent: Integrating BIM with Retrieval-Augmented Generation for Language GuidanceRetrieval-augmented generation → Agentic RAG, agents and memory +1
A Multi-Agent Approach to Neurological Clinical ReasoningLLM reasoning → Clinical and biomedical applications +1
CoMoE: Collaborative Optimization of Expert Aggregation and Offloading for MoE-based LLMs at EdgeMixture-of-experts → Efficient MoE training and inference systems
HSA-Net: Hierarchical and Structure-Aware Framework for Efficient and Scalable Molecular Language ModelingState-space sequence models (S4, Mamba) → Core SSM architectures for language
VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document UnderstandingRetrieval-augmented generation → Multimodal RAG
N-BEATS-MOE: N-BEATS with a Mixture-of-Experts Layer for Heterogeneous Time Series ForecastingMixture-of-experts → MoE for time series and graphs
AURA: A Fine-Grained Benchmark and Decomposed Metric for Audio-Visual ReasoningLLM reasoning → Audio-language model reasoning
CP-Agent: Agentic Constraint ProgrammingLLM agents and tool use → Software engineering coding agents
Grounding Natural Language for Multi-agent Decision-Making with Multi-agentic LLMsLLM agents and tool use → Reinforcement learning for LLM agents
Towards Unveiling Predictive Uncertainty Vulnerabilities in the Context of the Right to Be ForgottenLLM safety and security → Machine unlearning
Stackelberg Coupling of Online Representation Learning and Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
Let's Revise Step-by-Step: A Unified Local Search Framework for Code Generation with LLMsLLM reasoning → Reasoning for agents, planning and code
Freeze and Reveal: Exposing Modality Bias in Vision-Language ModelsMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
Grounding Multilingual Multimodal LLMs With Cultural KnowledgeMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
CLUE: Leveraging Low-Rank Adaptation to Capture Latent Uncovered Evidence for Image Forgery LocalizationDiffusion models → Image generation, text-to-image and editing
A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks +1
Efficient Reward Identification In Max Entropy Reinforcement Learning with Sparsity and Rank PriorsDeep reinforcement learning methods → RL for robot locomotion and manipulation
Parity Requires Unified Input Dependence and Negative Eigenvalues in SSMsState-space sequence models (S4, Mamba) → Core SSM architectures for language
Pentest-R1: Towards Autonomous Penetration Testing Reasoning Optimized via Two-Stage Reinforcement LearningLLM reasoning → Reasoning for agents, planning and code
Keyword Mamba: Spoken Keyword Spotting with State Space ModelsState-space sequence models (S4, Mamba) → Speech and audio SSMs
SODiff: Semantic-Oriented Diffusion Model for JPEG Compression Artifacts RemovalDiffusion models → Inverse problems and image restoration
A Survey on Agentic Service Ecosystems: Measurement, Analysis, and OptimizationLLM agents and tool use → General LLM agent frameworks and benchmarks
PrLM: Learning Explicit Reasoning for Personalized RAG via Contrastive Reward OptimizationLLM reasoning → Knowledge- and tool-augmented reasoning +2
Efficient Edge LLMs Deployment via HessianAware Quantization and CPU GPU CollaborativeMixture-of-experts → Efficient MoE training and inference systems
DocR1: Evidence Page-Guided GRPO for Multi-Page Document UnderstandingLLM reasoning → Multimodal reasoning +1
HealthBranches: Synthesizing Clinically-Grounded Question Answering Datasets via Decision PathwaysLLM reasoning → Clinical and biomedical applications
EndoCogniAgent: Closed-Loop Agentic Reasoning with Self-Consistency Validation for Endoscopic DiagnosisLLM reasoning → Clinical and biomedical applications +1
"Pull or Not to Pull?'': Investigating Moral Biases in Leading Large Language Models Across Ethical DilemmasLLM reasoning → Reasoning benchmarks and evaluation
Small-Large Collaboration: Training-efficient Concept Personalization for Large VLM using a Meta Personalized Small VLMMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Understanding Dynamic Scenes in Ego Centric 4D Point CloudsLLM reasoning → Spatial and embodied reasoning
Policy Newton methods for Distortion RiskmetricsDeep reinforcement learning methods → RL theory and sample complexity
Prompt Tuning for Few-Shot Continual Learning Named Entity RecognitionKnowledge distillation → Distillation for continual learning
Consistent and Controllable Image Animation with Motion Linear Diffusion TransformersDiffusion models → Video generation
Causal Negative Sampling via Diffusion Model for Out-of-Distribution RecommendationDiffusion models → Diffusion recommenders
ASM-UNet: Adaptive Scan Mamba Integrating Group Commonalities and Individual Variations for Fine-Grained SegmentationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
LP-Spec: Leveraging LPDDR PIM for Efficient LLM Mobile Speculative Inference with Architecture-Dataflow Co-OptimizationEfficient LLM inference and serving → Speculative decoding
Selection and Exploitation of High-Quality Knowledge from Large Language Models for RecommendationLLM reasoning → LLM reasoning for recommendation
LLM-based Agents for Automated Confounder Discovery and Subgroup Analysis in Causal InferenceLLM agents and tool use → Medical and scientific domain agents
Neural Bridge ProcessesDiffusion models → Diffusion foundations and sampling
Unsupervised Real-World Super-Resolution via Rectified Flow Degradation ModellingDiffusion models → Inverse problems and image restoration
Multi-Dimensional Summarization Agents with Context-Aware Reasoning over Enterprise TablesLLM reasoning → Reasoning for agents, planning and code +1
Explainability-in-Action: Enabling Expressive Manipulation and Tacit Understanding by Bending Diffusion Models in ComfyUIDiffusion models → Image generation, text-to-image and editing
Omni-SafetyBench: A Benchmark for Safety Evaluation of Audio-Visual Large Language ModelsLLM safety and security → Vision-language and text-to-image safety
Gradient Surgery for Safe LLM Fine-TuningLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
Integrating Neurosymbolic AI in Advanced Air Mobility: A Comprehensive SurveyLLM reasoning → Spatial and embodied reasoning
SketchAnimator: Animate Sketch via Motion Customization of Text-to-Video Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
Intention-Aware Diffusion Model for Pedestrian Trajectory PredictionDiffusion models → Diffusion and flow policies for robotics
Dynamic Pattern Alignment Learning for Pretraining Lightweight Human-Centric Vision ModelsMixture-of-experts → Vision mixture-of-experts
A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt DetectionLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
A Principled Loss Function for Direct Language Model AlignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
Perceptual Evaluation of GANs and Diffusion Models for Generating X-raysDiffusion models → Medical imaging and segmentation
Pref-GUIDE: Continual Policy Learning from Real-Time Human Feedback via Preference-Based LearningLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
Can LLMs Identify Tax Abuse?
Assessing and Mitigating Data Memorization Risks in Fine-Tuned Large Language Models
Activity Coefficient-based Channel Selection for Electroencephalogram: A Task-Independent Approach
Graph Neural Network for Product Recommendation on the Amazon Co-purchase Graph
AlphaEval: A Comprehensive and Efficient Evaluation Framework for Formula Alpha Mining
Enhancing Corrosion Resistance of Aluminum Alloys Through AI and ML Modeling
A Graph Neural Network based on a Functional Topology Model: Unveiling the Dynamic Mechanisms of Non-Suicidal Self-Injury in Single-Channel EEG
Modeling and Detecting Company Risks from News: A Case Study in Bloomberg News
Multi-task Adversarial Attacks against Black-box Model with Few-shot Queries
Certifiably robust malware detectors by design
Reflect then Learn: Active Prompting for Information Extraction Guided by Introspective Confusion
Quantum-Enhanced Generative Adversarial Networks: Comparative Analysis of Classical and Hybrid Quantum-Classical Generative Adversarial Networks
GANime: Generating Anime and Manga Character Drawings from Sketches with Deep Learning
The First Differentiable Transfer-Based Algorithm for Discrete MicroLED Repair
Position: Beyond Sensitive Attributes, ML Fairness Should Quantify Structural Injustice via Social Determinants
Normative Moral Pluralism for AI: A Framework for Deliberation in Complex Moral Contexts
Energy-Aware Code Generation with LLMs: Benchmarking Small vs. Large Language Models for Sustainable AI Programming
Synthesize, Retrieve, and Propagate: A Unified Predictive Modeling Framework for Relational Databases
Weather-Driven Agricultural Decision-Making Using Digital Twins Under Imperfect Conditions
Intersectoral Knowledge in AI and Urban Studies: A Framework for Transdisciplinary Research
Enhancing Privacy in Decentralized Min-Max Optimization: A Differentially Private Approach
FormCoach: Lift Smarter, Not Harder
VA-Blueprint: Uncovering Building Blocks for Visual Analytics System Design
Decomposing Global AUC into Cluster-Level Contributions for Localized Model Diagnostics
From Product Hilbert Spaces to the Generalized Koopman Operator and the Nonlinear Fundamental Lemma
Structured Superposition of Autoencoders for UEP Codes at Intermediate Blocklengths
Extracting Overlapping Microservices from Monolithic Code via Deep Semantic Embeddings and Graph Neural Network-Based Soft Clustering
Democratizing Diplomacy: A Harness for Evaluating Any Large Language Model on Full-Press Diplomacy
ALOPE: Adaptive Layer Optimization for Translation Quality Estimation using Large Language Models
Novel View Synthesis with Gaussian Splatting: Impact on Photogrammetry Model Accuracy and Resolution
Positional Biases Shift as Inputs Approach Context Window Limits
Online Convex Optimization with Heavy Tails: Old Algorithms, New Regrets, and Applications
MOTGNN: Interpretable Graph Neural Networks for Multi-Omics Disease Classification
Noise-Aware Generative Microscopic Traffic Simulation
Health Care Waste Classification Using Deep Learning Aligned with Nepal's Bin Color Guidelines
Leveraging Learning Bias for Noisy Anomaly Detection
Unsupervised operator learning approach for dissipative equations via Onsager principle
Lightning Prediction under Uncertainty: DeepLight with Hazy Loss
Real-Time Analysis of Unstructured Data with Machine Learning on Heterogeneous Architectures
Statistical Theory of Multi-stage Newton Iteration Algorithm for Online Continual Learning
Leveraging GNN to Enhance MEF Method in Predicting ENSO
CharacterShot: Controllable and Consistent 4D Character Animation
Event-Aware Sentiment Factors from LLM-Augmented Financial Tweets: A Transparent Framework for Interpretable Quant Trading
AgriVLN: Vision-and-Language Navigation for Agricultural Robots
Generative AI for Strategic Plan Development
ForensicsSAM: Toward Robust and Unified Image Forgery Detection and Localization Resisting to Adversarial Attack
LET-US: Long Event-Text Understanding of Scenes
A Spin Glass Characterization of Neural Networks

All 174