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: 27748 papers — Page 92 of 555
Many Steps into One: Reasoning Contraction and the Limits of Safe Memory Reuse for LLM Agents
Oct 13, 2026
4 authors
cs.CLcs.AI
FlashVSR+: Efficient Video Super-Resolution via Hybrid Attention and Reward-Yield Distribution Matching
Oct 13, 2026
10 authors
cs.CVcs.AI
EdgeWise: Bringing Long-Horizon Agents to the Edge via Selective Cloud Delegation
Oct 13, 2026
13 authors
cs.CL
Benchmarking Self-Supervised 3D Medical Vision Foundation Models and Transferability Estimation
Oct 13, 2026
10 authors
cs.CVcs.AI
Dissociating Answerability from Extraction in LLM Question Answering over Radiology Reports
Oct 13, 2026
2 authors
cs.CLcs.AIcs.LG
Risk-Averse Inference-Time Diffusion Model Alignment with Finite-Sample Guarantees
Oct 13, 2026
2 authors
stat.MLcs.LGmath.OC
Chasing Label Shifters: A Change-Aware Framework for Dynamic Graph Node Classification
Oct 13, 2026
4 authors
cs.LGcs.AI
RAN-JEPA: An Action-Conditioned World Model for Energy-efficient Mobile Network Control
Oct 13, 2026
6 authors
cs.AI
Taming Softmax at the Limits of Muon: A Unified Approach through Hilbert Geometry
Oct 13, 2026
5 authors
cs.LGcs.AI
Revisiting the 16x Pretraining Compute Gap between Diffusion and Autoregressive Language Models
Oct 13, 2026
6 authors
cs.LGcs.AI
Physical-Field-Bridged Material Parameter Inference from Multi-View Deformation Videos
Oct 13, 2026
4 authors
cs.CVcs.RO
Tanawpamana: Benchmarking Vision-Language Models on Philippine Cultural Heritage Sites
Oct 13, 2026
3 authors
cs.CVcs.AIcs.CL
Morphology-aware deep learning predicts colorectal cancer survival from whole-slide images
Oct 13, 2026
6 authors
cs.CVcs.AIcs.LG
PLEDGE: Progressive Lossy Error-Bounded Compression of 3D Gaussian Splatting
Oct 13, 2026
9 authors
cs.CV
Facts Don't Speak Louder than Words: The Behavioral Essence of Long-CoT Distillation
Oct 13, 2026
8 authors
cs.CL
Verifier-Harness Co-Evolution for Training-Free Self-Improvement on Open-Ended Tasks
Oct 13, 2026
9 authors
cs.AI
OpenDepth: Repurposing Image Editing Priors for Robust Open-World Monocular Depth Estimation
Oct 13, 2026
4 authors
cs.AI
MAS-Gate: Unlocking Multi-Agent System Lifecycle via Node-Centric Quantification
Oct 13, 2026
9 authors
cs.AIcs.MA
Background2Background: a self-supervised background removal framework for high dimensional microscopy
Oct 13, 2026
11 authors
eess.IVcs.CVphysics.optics
StateHarness: Maintaining Evolving Project State for Long-Horizon Coding Agents
Oct 13, 2026
4 authors
cs.SEcs.CL
When Does an ASR Error Matter? Task-Role Diagnostics for Tool-Using Voice Agents
Oct 13, 2026
3 authors
cs.CL
Smartphone-Based, Field-Deployed AI Inspection System for Power Distribution Infrastructure
Oct 13, 2026
6 authors
cs.CV
FedLoRD: Personalized Federated Learning based on Low-Rank Structures of Model Parameter Differences
Oct 13, 2026
4 authors
cs.LGeess.SP
RELAY: Selective Self-Distillation with Adaptive Hand-off for Rubric-Based Reinforcement Learning
Oct 13, 2026
10 authors
cs.LGcs.AIcs.CL
4LC: 4D Latent Cache for Efficient Conditioning in Dynamic World Modeling
Oct 13, 2026
5 authors
cs.CVcs.AI
From Pixels to Executable Physics: Behavior-Grounded World Models for Embodied Action Consequence Prediction
Oct 13, 2026
7 authors
cs.ROcs.CV
The Tokens Strike Back: Safety-Aware Denoising with Directional Embedding-based Revision
Oct 13, 2026
6 authors
cs.LGcs.AI
FrameLite: Decision-Oriented Aesthetic Cropping with a Compact Vision-Language Model
Oct 13, 2026
7 authors
cs.CV
MemAct: Streaming Spatial Understanding with Memory and Active Exploration
Oct 13, 2026
5 authors
cs.CV
Beyond Bias Scores: Answerability Confounds in Activation Steering with Gradient-Constrained Direction Design (GCD)
Oct 13, 2026
4 authors
cs.AI
When Should Enterprise Policy Decisions Be Learned, and When Should They Be Reasoned?
Oct 13, 2026
4 authors
cs.AI
DisaggKD: Efficient Knowledge Distillation through Teacher-Student Disaggregation and a Fused Loss
Oct 13, 2026
2 authors
cs.LGcs.CLcs.DC
Code2Worlds-2: Physically Plausible Agent Harness for Embodied World Simulation
Oct 13, 2026
6 authors
cs.ROcs.CV
Decouple to Forget: Semantic Mediation for Sensitive Unlearning in Large Language Models
Oct 13, 2026
10 authors
cs.CL
textGrain watermarking is harder to detect: can sum-tests still do it optimally?
Oct 13, 2026
2 authors
stat.MLcs.ITcs.LG+2
Open-o3-Video-v2: Seek, Ground, and Reason with Verifiable Spatio-Temporal Evidence
Oct 13, 2026
10 authors
cs.CV
ScenePercept: Scenario-Conditioned Perceptual Assessment of Real-World User-Generated Content Images
Oct 13, 2026
6 authors
cs.CV
The Image Still Has a Say: Final-Answer Repair for Multimodal Chain-of-Thought
Oct 13, 2026
3 authors
cs.CL
RoTA-Bench: Evaluating 3D Spatial Reasoning through Interactive Projection Alignment
Oct 13, 2026
10 authors
cs.AI
DeltaTTG: Training Multi-Turn Agents with a Token-to-Go Progress Meter
Oct 13, 2026
6 authors
cs.LGcs.AIcs.CL