UCLA_WHX's picture

UCLA_WHX

willhx

·

AI & ML interests

None yet

Recent Activity

authored a paper 1 day ago

T$^2$PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning

authored a paper 1 day ago

HarnessBridge: Learnable Bidirectional Controller for LLM Agent Harness

upvoted a paper 5 days ago

HarnessBridge: Learnable Bidirectional Controller for LLM Agent Harness

View all activity

Organizations

Collections 1

Papers 3

arxiv:2606.12882

arxiv:2605.02178

arxiv:2602.21534

models 6

willhx/Qwen3-4B-rft-webshop-5

4B • Updated May 1 • 418

willhx/Qwen3-4B-rft-alfworld-e5

4B • Updated May 1 • 3

willhx/Qwen3-30B-A3B_base_math_search

Text Generation • 31B • Updated Apr 17 • 550

willhx/Qwen3-4B-alfworld-finished

4B • Updated Mar 25 • 3

willhx/pokemon-lora

Updated Apr 28, 2023

willhx/train_lora

Text-to-Image • Updated Apr 18, 2023 • 3

datasets 2

willhx/sft_swe

Viewer • Updated Apr 8 • 8.35k • 12

willhx/SkyRL-SQL-Reproduction

Viewer • Updated Nov 20, 2025 • 5.91k • 19