YehuiTang

WizardTY

3 3

AI & ML interests

None yet

Recent Activity

posted an update 3 days ago

I built a scikit-learn for RSI. If you are learning RSI, comparing different RSI papers, build your own RSI algorithm, please try https://github.com/rsi-gear/gear. Don't forget to leave a star🌟!

liked a Space 8 days ago

WizardTY/GEAR

updated a Space 10 days ago

WizardTY/GEAR

View all activity

Organizations

None yet

posted an update 3 days ago

Post

I built a scikit-learn for RSI. If you are learning RSI, comparing different RSI papers, build your own RSI algorithm, please try https://github.com/rsi-gear/gear.
Don't forget to leave a star🌟!

liked a Space 8 days ago

GEAR

⚙

Recursive self-improvement of LLM agent harnesses

updated a Space 10 days ago

GEAR

⚙

Recursive self-improvement of LLM agent harnesses

published a Space 10 days ago

GEAR

⚙

Recursive self-improvement of LLM agent harnesses

upvoted a paper about 1 month ago

FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders

Paper • 2609.31620 • Published Sep 25 • 47

posted an update about 2 months ago

Post

If you want a hareness tuned for your scenario, try Gear. We just open-sourced a RSI infra for adapting agents to real-world tasks. On Automation bench, Gear-tuned DSH + Luna beats Astra + Codex on objective completion rate (84% vs 84%), with 95% lower API cost.

try Gear: https://github.com/rsi-gear/gear