When Does Longer Reasoning Help? Predicting Mathematical Reasoning Through Discovery and Execution
Research
Research News
New papers, breakthroughs and academic AI research
Task Vector Descent: Learning from Non-IID Batches
Research
Fitting Vision Adapters at Frontier Scales
Research
LoDEOT: Low-Dimensional and Efficient Offset Tokens for Building Footprint Extraction from Off-Nadir Imagery
Research
End-to-End Autonomous Recursive Arborescence Deformable Flow and Non-Linear Hemodynamics for Patient-Specific Coronary Centerline Extraction
Research
Safe Image Generation via Reinforcement Learning
Research
AstraSR: Real-World Thermal Super-Resolution with GPT-6 Astra
Research
Prompt and Refinement: Asymmetric Mutual Learning for Infrared Small Target Detection with Noisy Labels
Research
Every View Counts: View-Consistent Panoptic Quality for Multi-view Panoptic Segmentation
Research
UltraDub: Towards Authentic Dubbing by Unifying Visually-Steered Flow Learning and Trajectory Guidance
Research
OceanMind: A multi-agent AI system for ocean diagnosis
Research
From Requirements to Attack Trees: Grounded LLM Agents for Design-Time Security Review
Research