Changhao's picture

1 5

Changhao

lichangh20

·

https://lichangh20.github.io/

lichangh20

AI & ML interests

RL, Agent, Efficient ML

Recent Activity

upvoted an article about 2 months ago

Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment

upvoted a paper about 2 months ago

Matryoshka: Learning to Drive Black-Box LLMs with LLMs

upvoted a paper 3 months ago

MLE-Smith: Scaling MLE Tasks with Automated Multi-Agent Pipeline

View all activity

Organizations

lichangh20 's datasets 15

lichangh20/s1K_initial_filtered_for_llama8b

Viewer • Updated May 2, 2025 • 1k • 6

lichangh20/olympiadbench

Viewer • Updated Apr 22, 2025 • 674 • 16

lichangh20/minervamath

Viewer • Updated Apr 22, 2025 • 272 • 8

lichangh20/s1K_simplified_filtered_for_adapter

Viewer • Updated Mar 24, 2025 • 927 • 14

lichangh20/s1K_initial_filtered_for_qwen7b_simplified_summarized

Viewer • Updated Mar 15, 2025 • 997 • 7

lichangh20/s1K_initial_filtered_for_qwen7b_summarized

Viewer • Updated Mar 12, 2025 • 997 • 9

lichangh20/s1K_filtered_for_qwen7b_sft

Viewer • Updated Mar 11, 2025 • 899 • 13

lichangh20/s1k_eval_sampled_1of12

Viewer • Updated Mar 9, 2025 • 77 • 8

lichangh20/s1k_train_sampled_1of12

Viewer • Updated Mar 9, 2025 • 77 • 7

lichangh20/gpqa_sampled_1of3

Viewer • Updated Mar 9, 2025 • 66 • 12

lichangh20/openai_math_sampled_1of5

Viewer • Updated Mar 9, 2025 • 100 • 17

lichangh20/s1K_initial_filtered_for_adapter

Viewer • Updated Mar 5, 2025 • 929 • 7

lichangh20/s1K_initial_filtered_for_qwen7b

Viewer • Updated Feb 21, 2025 • 1k • 10

lichangh20/s1k_filtered_eval1K

Viewer • Updated Feb 12, 2025 • 929 • 12

lichangh20/s1k_filtered_full59K

Viewer • Updated Feb 12, 2025 • 54.2k • 8