Papers

New on arXiv

Sun 17 Aug 2025

147 papers

Generative Latent Diffusion Model for Inverse Modeling and Uncertainty Analysis in Geological Carbon SequestrationDiffusion models → Flow matching, time series and science
Cognitive Decision Routing in Large Language Models: When to Think Fast, When to Think SlowLLM reasoning → Test-time compute and efficient thinking
Meet Your New Client: Writing Reports for AI -- Benchmarking Information Loss in Market Research DeliverablesRetrieval-augmented generation → RAG pipeline design and evaluation
Accelerating LLM Inference via Dynamic KV Cache Placement in Heterogeneous Memory SystemEfficient LLM inference and serving → KV cache optimization
RISE: Enhancing VLM Image Annotation with Self-Supervised ReasoningLLM reasoning → Multimodal reasoning +1
MCPSecBench: A Systematic Security Benchmark and Playground for Testing Model Context ProtocolsLLM agents and tool use → Agent threats, guardrails and governance
Rethinking Safety in LLM Fine-tuning: An Optimization PerspectiveLLM reasoning → Reasoning for agents, planning and code
Results of the NeurIPS 2023 Neural MMO Competition on Multi-task Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
LangVision-LoRA-NAS: Neural Architecture Search for Variable LoRA Rank in Vision Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Mitigating Hallucinations in Large Language Models via Causal ReasoningLLM reasoning → Hallucination detection and mitigation
The Structural Sources of Verb Meaning Revisited: Large Language Models Display Syntactic BootstrappingSynthetic data and self-improvement for LLMs → LLM synthetic data generation
GALA: Can Graph-Augmented Large Language Model Agentic Workflows Elevate Root Cause Analysis?LLM agents and tool use → Software engineering coding agents
Is GPT-OSS Good? A Comprehensive Evaluation of OpenAI's Latest Open Source ModelsMixture-of-experts → MoE large language models
M3PO: Multimodal-Model-Guided Preference Optimization for Visual Instruction FollowingMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
X-Ray-CoT: Interpretable Chest X-ray Diagnosis with Vision-Language Models via Chain-of-Thought ReasoningLLM reasoning → Clinical and biomedical applications +1
Non-Interactive Symbolic-Aided Chain-of-Thought for Logical ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
LumiMAS: A Comprehensive Framework for Real-Time Monitoring and Enhanced Observability in Multi-Agent SystemsLLM agents and tool use → Software engineering coding agents
SRMA-Mamba: Spatial Reverse Mamba Attention Network for Pathological Liver Segmentation in MRI VolumesState-space sequence models (S4, Mamba) → Mamba for medical image analysis
ZigzagAttention: Efficient Long-Context Inference with Exclusive Retrieval and Streaming HeadsEfficient LLM inference and serving → KV cache optimization
LMAD: Integrated End-to-End Vision-Language Model for Explainable Autonomous DrivingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
MPCAR: Multi-Perspective Contextual Augmentation for Enhanced Visual Reasoning in Large Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
Federated Cross-Modal Style-Aware Prompt GenerationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Where to Start Alignment? Diffusion Large Language Model May Demand a Distinct PositionLLM safety and security → Safety alignment, refusal and guardrails
SIGN: Safety-Aware Image-Goal Navigation for Autonomous Drones via Reinforcement LearningDeep reinforcement learning methods → RL for robot navigation and UAV control
MedKGent: A Large Language Model Agent Framework for Constructing Temporally Evolving Medical Knowledge GraphLLM agents and tool use → Medical and scientific domain agents
ReaLM: Reflection-Enhanced Autonomous Reasoning with Small Language ModelsLLM reasoning → Reinforcement learning for reasoning
GraphCogent: Mitigating LLMs' Working Memory Constraints via Multi-Agent Collaboration in Complex Graph UnderstandingLLM agents and tool use → Web, search, and research agents
TaoSR1: The Thinking Model for E-commerce Relevance SearchLLM reasoning → Knowledge- and tool-augmented reasoning
Navigating the Exploration-Exploitation Tradeoff in Inference-Time Scaling of Diffusion ModelsLLM reasoning → Diffusion reasoning and test-time scaling +1
Synthetic Data is Sufficient for Zero-Shot Visual Generalization from Offline DataOffline RL and imitation learning from data → Offline RL algorithms +1
MBMamba: When Memory Buffer Meets Mamba for Structure-Aware Image DeblurringState-space sequence models (S4, Mamba) → Mamba for image restoration
Wisdom of the Crowd: Reinforcement Learning from Coevolutionary Collective FeedbackLLM reasoning → Reinforcement learning for reasoning +2
A Question Answering Dataset for Temporal-Sensitive Retrieval-Augmented GenerationLLM reasoning → Knowledge- and tool-augmented reasoning +1
LegalDelta: Enhancing Legal Reasoning in LLMs via Reinforcement Learning with Chain-of-Thought Guided Information GainLLM reasoning → Reasoning for agents, planning and code
The Self-Execution Benchmark: Measuring LLMs' Attempts to Overcome Their Lack of Self-ExecutionLLM reasoning → Reasoning benchmarks and evaluation
Fast, Slow, and Tool-augmented Thinking for LLMs: A ReviewLLM reasoning → Reasoning benchmarks and evaluation
Region-Level Context-Aware Multimodal UnderstandingMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Fortifying the Agentic Web: A Unified Zero-Trust Architecture Against Logic-layer ThreatsLLM agents and tool use → Agent threats, guardrails and governance
Structuring the Unstructured: A Systematic Review of Text-to-Structure Generation for Agentic AI with a Universal Evaluation FrameworkLLM agents and tool use → Web, search, and research agents
Robot Trains Robot: Automatic Real-World Policy Adaptation and Learning for HumanoidsDeep reinforcement learning methods → RL for robot locomotion and manipulation
STM3: Mixture of Multiscale Mamba for Long-Term Spatio-Temporal Time-Series PredictionState-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
LinkAnchor: An Autonomous LLM-Based Agent for Issue-to-Commit Link RecoveryLLM agents and tool use → Software engineering coding agents
Distribution Matching via Generalized Consistency ModelsDiffusion models → Flow matching, time series and science
Unlearning at Scale: State-Exact Trace-Preserving Deletion in Billion-Parameter Language ModelsLLM safety and security → Machine unlearning
Improving Pre-Trained Vision-Language-Action Policies with Model-Based SearchVision-language-action models → Reinforcement learning and post-training
Exploring Multimodal AI Reasoning for Meteorological Forecasting from Skew-T DiagramsLLM reasoning → Time series reasoning
Deep Learning and Matrix Completion-aided IoT Network Localization in the Outlier Scenarios
Empirical Analysis of the Effect of Context in the Task of Automated Essay Scoring in Transformer-Based Models
An Auditable Pipeline for Fuzzy Full-Text Screening in Systematic Reviews: Integrating Contrastive Semantic Highlighting and LLM Judgment
Straggler-Resilient Federated Learning over A Hybrid Conventional and Pinching Antenna Network
Research on intelligent generation of structural demolition suggestions based on multi-model collaboration
Better Together: Leveraging Multiple Digital Twins for Deployment Optimization of Airborne Base Stations
Disentangling the Drivers of LLM Social Conformity: An Uncertainty-Moderated Dual-Process Mechanism
High-Throughput Low-Cost Segmentation of Brightfield Microscopy Live Cell Images
You Don't Know Until You Click:Automated GUI Testing for Production-Ready Software Evaluation
PreSem-Surf: RGB-D Surface Reconstruction with Progressive Semantic Modeling and SG-MLP Pre-Rendering Mechanism
A Recurrent Neural Network based Clustering Method for Binary Data Sets in Education
MIRAGE: Towards AI-Generated Image Detection in the Wild
Deep Graph Neural Point Process For Learning Temporal Interactive Networks
The Course Difficulty Analysis Cookbook
Strategies for training point distributions in physics-informed neural networks
Defining and Benchmarking a Data-Centric Design Space for Brain Graph Construction
Toward Architecture-Agnostic Local Control of Posterior Collapse in VAEs
MuSACo: Multimodal Subject-Specific Selection and Adaptation for Expression Recognition with Co-Training
An Initial Study of Bird's-Eye View Generation for Autonomous Vehicles using Cross-View Transformers
An Introduction to Sliced Optimal Transport
Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and Inference
Segmenting Thalamic Nuclei: T1 Maps Provide a Reliable and Efficient Solution
Design and Validation of a Responsible Artificial Intelligence-based System for the Referral of Diabetic Retinopathy Patients
Root Cause Analysis of Hydrogen Bond Separation in Spatio-Temporal Molecular Dynamics using Causal Models
Cost-Aware Contrastive Routing for LLMs
Advanced DOA Regulation with a Whale-Optimized Fractional Order Fuzzy PID Framework
Cold-RL: Learning Cache Eviction with Offline Reinforcement Learning for NGINX
Skin Cancer Classification: Hybrid CNN-Transformer Models with KAN-Based Fusion
Simultaneous estimation of connectivity and dimensionality in samples of networks
The Yokai Learning Environment: Tracking Beliefs Over Space and Time
EXOTIC: An Exact, Optimistic, Tree-Based Algorithm for Min-Max Optimization
SimQFL: A Quantum Federated Learning Simulator with Real-Time Visualization
Standardization of Neuromuscular Reflex Analysis -- Role of Fine-Tuned Vision-Language Model Consortium and OpenAI gpt-oss Reasoning LLM Enabled Decision Support System
A Robust Cross-Domain IDS using BiGRU-LSTM-Attention for Medical and Industrial IoT Security
Mechanical Automation with Vision: A Design for Rubik's Cube Solver
Inverse-LLaVA: Rethinking Multimodal Alignment via Text-to-Vision Mapping
LoraxBench: A Multitask, Multilingual Benchmark Suite for 20 Indonesian Languages
Local Cluster Cardinality Estimation for Adaptive Mean Shift
Uncovering Spontaneous Physics Representations in In-Context Learning
FractMorph: A Fractional Fourier-Based Multi-Domain Transformer for Deformable Image Registration
Machine Learning-Based Manufacturing Cost Prediction from 2D Engineering Drawings via Geometric Features
Express4D: Expressive, Friendly, and Extensible 4D Facial Motion Generation Benchmark
Tactile Gesture Recognition with Built-in Joint Sensors for Industrial Robots
Adversarial Attacks on VQA-NLE: Exposing and Alleviating Inconsistencies in Visual Question Answering Explanations
Asymptotic breakdown point analysis of the minimum density power divergence estimator under independent non-homogeneous setups
Illusions in Humans and AI: How Visual Perception Aligns and Diverges
Bi-Axial Transformers: Addressing the Increasing Complexity of EHR Classification
fCrit: A Visual Explanation System for Furniture Design Creative Support
TiP4GEN: Text to Immersive Panorama 4D Scene Generation
Quantum Flow Matching
The Cultural Gene of Large Language Models: A Study on the Impact of Cross-Corpus Training on Model Values and Biases
S5: Scalable Semi-Supervised Semantic Segmentation in Remote Sensing
Extracting Post-Acute Sequelae of SARS-CoV-2 Infection Symptoms from Clinical Notes via Hybrid Natural Language Processing
DeCoT: Decomposing Complex Instructions for Enhanced Text-to-Image Generation with Large Language Models

All 147