AI Research Papers
Explore the latest research papers from arXiv in artificial intelligence, machine learning, and related fields. Discover cutting-edge research from top institutions and researchers worldwide. Total: 26785 papers — Page 344 of 536
Listen Then Reason: Perception-Grounded Test-Time Reinforcement Learning for Large Audio-Language Models
Sep 20, 2026
6 authors
cs.SDcs.AIeess.AS
Cost-Aware Reinforcement Learning with Action Masking and Projection for Battery Energy Storage Dispatch under Suppressed-Spread Market Shifts
Sep 20, 2026
3 authors
cs.LGcs.AIeess.SY
Collapse, Not Complexity: Failure-Conditioned Decomposition Repair for End-to-End Document Parsing
Sep 20, 2026
2 authors
cs.CVcs.CL
Bilinear Optimization Divergence: Diagnosing Factor-Constrained LoRA Continual Learning
Sep 20, 2026
3 authors
cs.LG
PETR: Prompt Ensembling with Training-free Routing for Vision-Language Models
Sep 20, 2026
5 authors
cs.CVcs.AI
Beyond UV Mapping: Mesh Texture Compression via Surface-Aligned Texture Fields
Sep 20, 2026
5 authors
cs.CV
Rachel: A general-purpose language model directs and revises retrosynthetic routes
Sep 20, 2026
6 authors
physics.chem-phcs.AI
Compact Low-Cost Hyperspectral Imaging via Angular-to-Spectral Diversity Conversion
Sep 20, 2026
5 authors
cs.CV
Are Human-Aligned Models Models of Humans? A Turing-Test Gap in Preference Alignment
Sep 20, 2026
8 authors
cs.AIcs.CLcs.LG
Spiking Neural Network Actor-Critic Proximal Policy Optimization Control for Autonomous UAV Navigation Through Constrained Openings in Civil Infrastructure and Buildings
Sep 20, 2026
4 authors
cs.ROcs.AI
Beyond Relevance: Structured Semantic Supervision for Product Search with LLM-Augmented Annotations
Sep 20, 2026
7 authors
cs.IRcs.CL
Beyond Appearance Shifts: Task-Semantic Action Calibration for VLA Models
Sep 20, 2026
8 authors
cs.ROcs.LG
Reassessing Global Gradient-Norm Imbalance in BLIP Fine-Tuning Across Physical Domains
Sep 20, 2026
3 authors
cs.CV
Why Do Video Diffusion Models Violate Physics? Unveiling the Flaws in Attention Mechanisms
Sep 20, 2026
4 authors
cs.CVcs.LG
ETH-TraceBench: A Large-Scale Event-Stream Benchmark for Ethereum DeFi under Temporal, Protocol, and Contract Shift
Sep 20, 2026
2 authors
cs.LG
Which Constraints Are Missing? Ask the Verifier: Graded Rewards for Constraint-Following Music Generation
Sep 20, 2026
6 authors
cs.SDcs.AI
Which Terrain Is Better? Preference Learning with VLM Prototypes for Off-Road Traversability Ranking
Sep 20, 2026
6 authors
cs.CVcs.RO
One Patch, Three Roles: What Is Actually Coupled in Autoregressive Time-Series Forecasting?
Sep 20, 2026
7 authors
cs.LG
A multi-temporal dataset for mapping burned areas in the Brazilian Cerrado using time series of remote sensing imagery
Sep 20, 2026
2 authors
cs.LGcs.AIcs.CV
Text Scores Can Miss Waveform Use: A Qwen2-Audio Quantization Case Study
Sep 20, 2026
3 authors
cs.SDcs.CLeess.AS
Tail-Weight Control and Localized Generalization in Nearly Low-Rank Adversarial Classification
Sep 20, 2026
3 authors
cs.LGcs.AI
PhysAI-Bench: A Benchmark for LLM-Based Agentic Decision-Making in Autonomous UAV-Centric Physical AI
Sep 20, 2026
5 authors
cs.AI
Distill What You Trust: Reliability-Aware Multi-Teacher On-Policy Distillation
Sep 20, 2026
11 authors
cs.CLcs.LG
When the Agent Becomes the Kernel: A Systematization of Security on the Path to AI-Native Operating Systems
Sep 20, 2026
3 authors
cs.CRcs.AIcs.OS
TEMPER: Temporal Encoder-Masked Probabilistic Ensemble Regressor for Time-Series Forecasting
Sep 20, 2026
1 authors
stat.MLcs.LG
Financial Language Models as Applied Artificial Intelligence Systems for News-Based Trading under Market Frictions
Sep 20, 2026
1 authors
cs.CLcs.LGq-fin.TR
Infectious Bovine Pinkeye Detection Using Computer Vision and Imbalance-Aware Learning
Sep 20, 2026
3 authors
cs.CV
Layer-Aware Position Embeddings for Visual Token Pruning in Multimodal Large Language Models
Sep 20, 2026
6 authors
cs.CV
STEVE: Stabilizing Textual Gradient-Based Prompt Optimization via Error-Driven Refinement and Regularized Verification
Sep 20, 2026
7 authors
cs.CLcs.AIcs.LG
What Makes a Terminal-Bench Task Hard? Separating Genuine Hardness from Fake-Hardness on an Adjudicated Agentic Corpus
Sep 20, 2026
7 authors
cs.LGcs.AI
WILSON - a pathology foundation model framework for patient-level analysis and diagnostic text generation
Sep 20, 2026
16 authors
q-bio.QMcs.AIcs.CV+2
Marginal Calibration Does Not Compose: Hidden Dependence in Modular Robot Navigation
Sep 20, 2026
1 authors
cs.ROcs.LG
Constructing Challenging Browser-Use Tasks by Controlled Environment Interventions
Sep 20, 2026
11 authors
cs.CLcs.AI
VGGT-Prime: Compute-Adaptive Mixture-of-Heads for Efficient Visual Geometry Transformers
Sep 20, 2026
4 authors
cs.CV
ScholarStack: Layered Research Asset Orchestration and Cross-Task Reuse for Scientific Agents
Sep 20, 2026
20 authors
cs.AI
Constrained Decoding Eliminates Structural Failures in Small LLMs but Reveals a Scale-Dependent Semantic Gap
Sep 20, 2026
1 authors
cs.CL
How to Run Statistics over LLM Judges and Trust the Results: Calibrated Inference for Small-Sample AI Evaluation with evalstats
Sep 20, 2026
1 authors
cs.CLcs.AIcs.HC+1
Cross-Dataset Generalization of Bangladeshi Rice Leaf Disease Classifiers: Benchmark, Diagnosis, and Mitigation
Sep 20, 2026
1 authors
cs.CV
OnlineWM: Causality-Aware Active Online Learning for Effective World Modeling
Sep 20, 2026
9 authors
cs.CVcs.LG