Privileged Context as Drift in On-Policy Self-Distillation
Research
Research News
New papers, breakthroughs and academic AI research
Generalized Matheron Variational Implicit Processes
Research
SquidAgent: Parallelize Wisely, Coordinate Efficiently
Research
A Decision-Focused Neural Optimization Framework for Personalized Route Reproduction from Vehicle Trajectories
Research
FC-SWE: Failure-Conditioned RL for Long-Horizon Software Engineering Agents
Research
Align, Then Correct: Training-Free Two-Stage Low-Rank Compensation for Extremely Quantized Large Language Models
Research
ALIVE: Interaction-Aligned Object Insertion for First-Frame-Guided Video Editing
Research
On-Policy Distillation with Negative-Policy Rollouts
Research
Building Rome from a Single Image
Research
4D-HOF: Hand-Object Flow Matching for Feed-Forward 4D Interaction Reconstruction
Research
Label-Efficient Deep Learning for ECG Delineation: A Multi-Dataset Benchmark against Widely Used Delineation Tools
Research
A Systematic Study of Small Language Models on Abstract Reasoning Tasks
Research