Papers

New on arXiv

Sun 31 Aug 2025

174 papers

RLFactory: A Plug-and-Play Reinforcement Learning Post-Training Framework for LLM Multi-Turn Tool-UseLLM reasoning → Reinforcement learning for reasoning +1
Energy Landscapes Enable Reliable Abstention in Retrieval-Augmented Large Language Models for HealthcareRetrieval-augmented generation → Medical and biomedical RAG
Radio Astronomy in the Era of Vision-Language Models: Prompt Sensitivity and AdaptationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Reinforcement Learning Driven Generalizable Feature Representation for Cross-User Activity RecognitionDeep reinforcement learning methods → Deep RL algorithms and representations
Any-Order Flexible Length Masked DiffusionDiffusion models → Discrete and text diffusion
Supporting Our AI Overlords: Redesigning Data Systems to be Agent-FirstLLM agents and tool use → Web, search, and research agents
MEPT: Mixture of Expert Prompt Tuning as a Manifold MapperMixture-of-experts → Mixture of LoRA experts
Causal MAS: A Survey of Large Language Model Architectures for Discovery and Effect EstimationLLM agents and tool use → Medical and scientific domain agents
RPRO: Ranked Preference Reinforcement Optimization for Enhancing Medical QA and Diagnostic ReasoningLLM reasoning → Clinical and biomedical applications +1
CoreThink: A Symbolic Reasoning Layer to reason over Long Horizon Tasks with LLMsLLM reasoning → Reasoning benchmarks and evaluation
Seeing More, Saying More: Lightweight Language Experts are Dynamic Video Token CompressorsEfficient LLM inference and serving → Visual token pruning in multimodal models
SCOUT: Toward Sub-Quadratic Attention via Segment Compression for Optimized Utility in TransformersState-space sequence models (S4, Mamba) → Core SSM architectures for language
SATQuest: A Verifier for Logical Reasoning Evaluation and Reinforcement Fine-Tuning of LLMsLLM reasoning → Reasoning benchmarks and evaluation
EviNote-RAG: Enhancing RAG Models via Answer-Supportive Evidence NotesRetrieval-augmented generation → RAG robustness and adaptive retrieval
Look Beyond: Two-Stage Scene View Generation via Panorama and Video DiffusionDiffusion models → 3D, point cloud and scene generation
CogDriver: Integrating Cognitive Inertia for Temporally Coherent Planning in Autonomous DrivingMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
Image-to-Brain Signal Generation for Visual Prosthesis with CLIP Guided Multimodal Diffusion ModelsDiffusion models → Medical imaging and segmentation
Aligning Reasoning LLMs for Materials Discovery with Physics-aware Rejection SamplingLLM reasoning → Clinical and biomedical applications
InterPose: Learning to Generate Human-Object Interactions from Large-Scale Web VideosDiffusion models → Video generation
L-MARS: Legal Multi-Agent System with Agentic Search and Citation-Faithfulness AuditLLM agents and tool use → Social simulation and multi-agent debate
MarkSplatter: Generalizable Watermarking for 3D Gaussian Splatting Model via Splatter Image StructureLLM safety and security → Watermarking generated content and models
Causal Interpretation of Sparse Autoencoder Features in VisionMechanistic interpretability → Interpreting vision and multimodal models
OmniDPO: A Preference Optimization Framework to Address Omni-Modal HallucinationLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
It's-A-Me, Quantum Mario: Scalable Quantum Reinforcement Learning with Multi-Chip EnsemblesDeep reinforcement learning methods → Quantum reinforcement learning
Reward-Weighted Sampling: Enhancing Non-Autoregressive Characteristics in Masked Diffusion LLMsDiffusion models → Discrete and text diffusion +1
Prompt the Unseen: Evaluating Visual-Language Alignment Beyond SupervisionMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Learning to Shop Like Humans: A Review-driven Retrieval-Augmented Recommendation Framework with LLMsRetrieval-augmented generation → RAG for recommendation
CE-Bench: Towards a Reliable Contrastive Evaluation Benchmark of Interpretability of Sparse AutoencodersMechanistic interpretability → SAE features and their applications
Router Upcycling: Leveraging Mixture-of-Routers in Mixture-of-Experts UpcyclingMixture-of-experts → Expert routing strategies
CSFMamba: Cross State Fusion Mamba Operator for Multimodal Remote Sensing Image ClassificationState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy ModelMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
Confident, Calibrated, or Complicit: Safety Alignment and Ideological Bias in LLM Hate Speech DetectionLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment +1
Fusion to Enhance: Fusion Visual Encoder to Enhance Multimodal Language ModelMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
RAG-PRISM: A Personalized, Rapid, and Immersive Skill Mastery Framework with Adaptive Retrieval-Augmented TutoringRetrieval-augmented generation → Agentic RAG, agents and memory
A Multimodal GUI Architecture for Interfacing with LLM-Based Conversational Assistants
Towards Repository-Level Program Verification with Large Language Models
Scaling Up Data Parallelism in Decentralized Deep Learning
SOH-KLSTM: A Hybrid Kolmogorov-Arnold Network and LSTM Model for Enhanced Lithium-Ion Battery Health Monitoring
Moment Estimates and DeepRitz Methods on Learning Diffusion Systems with Non-gradient Drifts
DeepSeasons: a Deep Learning scale-selecting approach to Seasonal Forecasts
Online Learning Based Efficient Resource Allocation for LoRaWAN Network
FlowECG: Using Flow Matching to Create a More Efficient ECG Signal Generator
Distributed Gossip-GAN for Low-overhead CSI Feedback Training in FDD mMIMO-OFDM Systems
Exploring Over-stationarization in Deep Learning-based Bus/Tram Arrival Time Prediction: Analysis and Non-stationary Effect Recovery
Integrated Simulation Framework for Adversarial Attacks on Autonomous Vehicles
ForensicsData: A Digital Forensics Dataset for Large Language Models
MVRS: The Multimodal Virtual Reality Stimuli-based Emotion Recognition Dataset
Optical Music Recognition of Jazz Lead Sheets
Feed Two Birds with One Scone: Exploiting Function-Space Regularization for Both OOD Robustness and ID Fine-Tuning Performance
Layer-Wise Anomaly Detection in Directed Energy Deposition using High-Fidelity Fringe Projection Profilometry
ASCENDgpt: A Phenotype-Aware Transformer Model for Cardiovascular Risk Prediction from Electronic Health Records
The Good, the Bad and the Constructive: Automatically Measuring Peer Review's Utility for Authors
DecMetrics: Structured Claim Decomposition Scoring for Factually Consistent LLM Outputs
Narrative-to-Scene Generation: An LLM-Driven Pipeline for 2D Game Environments
Improving Factuality in LLMs via Inference-Time Knowledge Graph Construction
Use ADAS Data to Predict Near-Miss Events: A Group-Based Zero-Inflated Poisson Approach
CompSlider: Compositional Slider for Disentangled Multiple-Attribute Image Generation
Symbolic Planning and Multi-Agent Path Finding in Extremely Dense Environments with Unassigned Agents
Quantum-like Coherence Derived from the Interaction between Chemical Reaction and Its Environment
AI-driven Dispensing of Coral Reseeding Devices for Broad-scale Restoration of the Great Barrier Reef
Analysis of Error Sources in LLM-based Hypothesis Search for Few-Shot Rule Induction
Weather-Dependent Variations in Driver Gaze Behavior: A Case Study in Rainy Conditions
Ranking of Bangla Word Graph using Graph-based Ranking Algorithms
Quantum-based QoE Optimization in Advanced Cellular Networks: Integration and Cloud Gaming Use Case
Generalized promotion time cure model: A new modeling framework to identify cell-type-specific genes and improve survival prognosis
Online Decentralized Federated Multi-task Learning With Trustworthiness in Cyber-Physical Systems
Hybrid Topic-Semantic Labeling and Graph Embeddings for Unsupervised Legal Document Clustering
Towards Integrating Multi-Spectral Imaging with Gaussian Splatting
Performance Analysis of Supervised Machine Learning Algorithms for Text Classification
IoT-based Noise Monitoring using Mobile Nodes for Smart Cities
Self-Exploring Language Models for Explainable Link Forecasting on Temporal Graphs via Reinforcement Learning
Clone What You Can't Steal: Black-Box LLM Replication via Logit Leakage and Distillation
Who Gets Left Behind? Auditing Disability Inclusivity in Large Language Models
Ultra Strong Machine Learning: LLM-Generated Explanations Do Not Yet Suffice for Teaching Humans Active Learning Strategy
A Hybrid Ai Framework For Strategic Patent Portfolio Pruning: Integrating Learning To-Rank And Market Need Analysis For Technology Transfer Optimization
ART: Adaptive Resampling-based Training for Imbalanced Classification
Structure and Destructure: Dual Forces in the Making of Knowledge Engines
Ultrasound-based detection and malignancy prediction of breast lesions eligible for biopsy: A multi-center clinical-scenario study using nomograms, large language models, and radiologist evaluation
Protocol for Clustering 4DSTEM Data for Phase Differentiation in Glasses
Regime-Switching Langevin Monte Carlo Algorithms
UrbanInsight: A Distributed Edge Computing Framework with LLM-Powered Data Filtering for Smart City Digital Twins
MedCOD: Enhancing English-to-Spanish Medical Translation of Large Language Models Using Enriched Chain-of-Dictionary Framework
Semi-Supervised Bayesian GANs with Log-Signatures for Uncertainty-Aware Credit Card Fraud Detection
Superposition in Graph Neural Networks
DTRNet: Dynamic Token Routing Network to Reduce Quadratic Costs in Transformers
Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data
Robust Deep Monte Carlo Counterfactual Regret Minimization: Addressing Theoretical Risks in Neural Fictitious Self-Play
Supervised In-Context Fine-Tuning for Generative Sequence Labeling
DarkVRAI: Capture-Condition Conditioning and Burst-Order Selective Scan for Low-light RAW Video Denoising
TinyMusician: On-Device Music Generation with Knowledge Distillation and Mixed Precision Quantization
GS-TG: 3D Gaussian Splatting Accelerator with Tile Grouping for Reducing Redundant Sorting while Preserving Rasterization Efficiency
Spotlighter: Revisiting Prompt Tuning from a Representative Mining View
Learning with Mandelbrot and Julia
Towards Early Detection: AI-Based Five-Year Forecasting of Breast Cancer Risk Using Digital Breast Tomosynthesis Imaging
SeLeRoSa: Sentence-Level Romanian Satire Detection Dataset
ChatCLIDS: Simulating Persuasive AI Dialogues to Promote Closed-Loop Insulin Adoption in Type 1 Diabetes Care
An Explainable Gaussian Process Auto-encoder for Tabular Data
Accelerating Latency-Critical Applications with AI-Powered Semi-Automatic Fine-Grained Parallelization on SMT Processors
Tabular Diffusion Counterfactual Explanations
Pose as Clinical Prior: Learning Dual Representations for Scoliosis Screening

All 174