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 287 of 536
Phase Space Attention:A Hairer Lift Circumvents the Single-Layer Induction Obstruction
Sep 26, 2026
4 authors
cs.LGcond-mat.mtrl-scics.AI
Not All Errors Matter: Decision-Relevant Prediction Error Predicts Planning Quality
Sep 26, 2026
3 authors
cs.LG
FoundDSR: A Generalizable Foundation Model with Guided 2D Gaussian Splatting for Depth Super-Resolution
Sep 26, 2026
6 authors
cs.CV
RLHarness: Co-evolving Procedural Skills with Reinforcement Learning for Long-horizon Multimodal Reasoning
Sep 26, 2026
9 authors
cs.AI
Continual Data Unlearning in Diffusion Models via Transition-based Regularization
Sep 26, 2026
4 authors
cs.LG
HyperReCo: Retrieving and Connecting Evidence with Hypergraph Neural Networks for LLM Multi-hop Reasoning
Sep 26, 2026
7 authors
cs.AI
When the Merge Coefficient Stops Mattering: Proximity Regularized Merging for Continual LoRA Adaptation
Sep 26, 2026
4 authors
cs.LG
Progressive-View On-Policy Distillation for Regional-to-Global Transfer in Multimodal LLMs
Sep 26, 2026
4 authors
cs.CVcs.AI
Enabling Timely Guidance before Skill Retrieval: Retaining Helpful Warm Tips in Agent Context
Sep 26, 2026
5 authors
cs.AIcs.MA
A Comparative Analysis of Attention versus State-Space Models for In-Context Learning
Sep 26, 2026
3 authors
cs.LG
OpenMASC: An Open-Source Pipeline for Cross-Trajectory Metal-Aware Sampling and Correction in Accelerated MRI
Sep 26, 2026
14 authors
cs.CV
Analog-Friendly Predictive Coding without Activation Derivatives
Sep 26, 2026
1 authors
cs.LGcs.AIcs.NE
From Trajectories to Grounded Preferences: Process Preference Synthesis via Interaction Element Graphs for Web PRMs
Sep 26, 2026
5 authors
cs.AI
EyeVQA: Benchmarking Ophthalmic Vision-Language Models from Recognition to Spatial Grounding
Sep 26, 2026
10 authors
cs.CVcs.AI
Fewer Tokens, More Self-Teaching: On-Policy Self-Distillation for Extreme Visual Token Reduction
Sep 26, 2026
6 authors
cs.CVcs.CLcs.LG
Gradients for Interventions and Activations for Detection: Targeted Feature Learning in Language Models
Sep 26, 2026
2 authors
cs.CLcs.LG
Editable Map-Conditioned Trajectory Generation for Human Mobility Simulation
Sep 26, 2026
4 authors
cs.LGcs.CYphysics.soc-ph
Black-Box Auditing of Epistemic Reliability in Multi-Agent Debate Distillation
Sep 26, 2026
7 authors
cs.LGcs.AIcs.CL+1
DiffPTS: Rethinking Diffusion ELBO for Probabilistic Time Series Forecasting
Sep 26, 2026
6 authors
cs.LGcs.AI
STRIDE: State-Transition Representation via Increment Dynamics and Evolution
Sep 26, 2026
3 authors
cs.LG
Authority Before Utility: Non-Compensatory Control for Persistent LLM Memory
Sep 26, 2026
1 authors
cs.AI
Boundary-State Control for Tool-Using Language-Model Agents: Commit-Time Consistency under State Drift
Sep 26, 2026
1 authors
cs.AI
An End-to-End Latent-Rollout Approach for Pushing Few-Step ImageNet-$256$ Generation to FID $1.11$ without Fréchet Losses
Sep 26, 2026
2 authors
cs.CV
AuthorityLens: Rethinking LLM-Based Agent Systems Through the Lens of Authority
Sep 26, 2026
10 authors
cs.AI
Measurement Boundaries in LLM Financial Agent Evaluation: Fixed-Tape Execution and Multi-Defect Auditing
Sep 26, 2026
1 authors
cs.LGcs.AIcs.CE+1
Attribution Without a Second Pass: Inline Per-Sample Gradient Provenance at ~1% Overhead
Sep 26, 2026
1 authors
cs.LG
PlurVA-LLM-2026 Shared Task Track-1: Pluralistic Value Alignment in LLMs via Multilingual Fine-Tuning and Threshold Calibration
Sep 26, 2026
2 authors
cs.CL
TimeES: Probabilistic and Deterministic Time Series Forecasting via Evolutionary Spectra
Sep 26, 2026
5 authors
cs.LGcs.AI
DashAct: A Progressive Diagnostic Benchmark for GUI Agents in Interactive Dashboard Analysis
Sep 26, 2026
7 authors
cs.HCcs.AI
Using Machine Learning to Investigate Predictors of Fasting Blood Glucose: Insights into Circadian Timing and Age Interactions
Sep 26, 2026
2 authors
cs.LG
RefCompose: Multi-Reference Image Generation via LoRA-Conditioned Diffusion
Sep 26, 2026
5 authors
cs.CVeess.IV
Reward Hacking and Agent Containment Failure: A Monte Carlo Study Based on the 2026 Hugging Face Incident
Sep 26, 2026
3 authors
cs.AIcs.CR
SCLATE: a Substrate for Continual-Learning Agent Training and Evaluation
Sep 26, 2026
6 authors
cs.AIcs.DCcs.LG
Convergent Plug-and-Play Image Restoration with Annealed Noise Levels
Sep 26, 2026
1 authors
math.OCcs.LG
Beyond Scripted Search: Sample-Efficient Reward Discovery via Agentic Black-box Optimization
Sep 26, 2026
3 authors
cs.AI
FA-Bench: A Benchmark for Word-Level and Phone-Level Forced-Alignment and ASR Timestamps Under Clean and Noisy Conditions
Sep 26, 2026
14 authors
cs.CLcs.PF
SinBrief: A Hybrid Framework for Abstractive Text Summarisation of Sinhala Legal Documents
Sep 26, 2026
2 authors
cs.CL
Function Over Form: Distributional Orthogonalization in Mixture-of-Experts with Replica Expert Mechanism
Sep 26, 2026
6 authors
cs.AI
Endo-TSR: Temporal Spectral Modeling of Appearance and Motion for Endoscopic Reconstruction
Sep 26, 2026
7 authors
cs.CVcs.RO
SkillDRE: Dual-Stage Red-Team Evolution of Agent Skills via Pre-Execution and Runtime Feedback
Sep 26, 2026
5 authors
cs.CRcs.AI