梁宇航

tongjirobotics

7 5

·

AI & ML interests

Interested in machine learning, NLP and open source AI.

Recent Activity

upvoted a paper about 12 hours ago

VisionHOPE: Visual Backbones as Self-Modifying Learning Systems

upvoted a paper about 12 hours ago

The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation

updated a dataset 10 days ago

tongjirobotics/image-depth-samples

View all activity

Organizations

None yet

upvoted 2 papers about 12 hours ago

VisionHOPE: Visual Backbones as Self-Modifying Learning Systems

Paper • 2609.33325 • Published 14 days ago • 295

The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation

Paper • 2609.36484 • Published 12 days ago • 528

upvoted 3 papers 10 days ago

LEGO-Anything: Coding Agents for 3D Scene Reconstruction

Paper • 2609.36380 • Published 13 days ago • 130

MaLiang-Harness: A Programmable Path to Image and Video Generation

Paper • 2609.34309 • Published 13 days ago • 394

In-Context Learning for Robots: Methods and Applications

Paper • 2609.36012 • Published 13 days ago • 322

upvoted 2 papers about 2 months ago

Alaya-EVOKE: From Linear-Scaling Supervision to Endless World

Paper • 2608.13546 • Published Aug 13 • 114

Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs

Paper • 2608.20492 • Published Aug 20 • 67