Rushuai Yang

Rushuai

9 2

AI & ML interests

None yet

Recent Activity

upvoted a paper 10 days ago

Rollback: Experience Backtracking in World Models for Policy Improvement

upvoted a paper 18 days ago

Learning from Fleet Experience: A Collective Learning Paradigm for Robots

upvoted a paper 18 days ago

HarnessPro: Recursive Harness Self-Improvement with Pareto Optimization for Performance-Cost Trade-offs

View all activity

Organizations

None yet

upvoted a paper 10 days ago

Rollback: Experience Backtracking in World Models for Policy Improvement

Paper • 2610.36068 • Published 12 days ago • 54

upvoted 3 papers 18 days ago

Learning from Fleet Experience: A Collective Learning Paradigm for Robots

Paper • 2610.25736 • Published 19 days ago • 113

HarnessPro: Recursive Harness Self-Improvement with Pareto Optimization for Performance-Cost Trade-offs

Paper • 2610.26770 • Published 19 days ago • 33

EnactOpt: Diagnosis-Guided Harness Evolution for Embodied Agents

Paper • 2610.14977 • Published 28 days ago • 6

upvoted a paper 9 months ago

ALOE: Action-Level Off-Policy Evaluation for Vision-Language-Action Model Post-Training

Paper • 2602.12691 • Published Feb 13 • 1

upvoted a paper about 1 year ago

Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR

Paper • 2508.14029 • Published Aug 19, 2025 • 101

upvoted 2 papers over 1 year ago

Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling

Paper • 2507.07982 • Published Jul 10, 2025 • 34

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Paper • 2502.06703 • Published Feb 10, 2025 • 150

upvoted an article almost 2 years ago

Article

Sales Forecasting with Image Regression

tonyassi

•

May 24, 2024

• 9