Shiyu's Lab

university

https://code-terminator.github.io/

AI & ML interests

None defined yet.

Papers

How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings

View all Papers

Collections 3

View 3 collections

models 30

Shiyu-Lab/HarnessLLM_SFT_Llama3_3B

4B • Updated Nov 2, 2025 • 5

Shiyu-Lab/Inputoutput_SFT_Llama3_3B

4B • Updated Nov 2, 2025 • 4

Shiyu-Lab/Inputoutput_SFT_Qwen3_4B

4B • Updated Nov 2, 2025 • 8

Shiyu-Lab/HarnessLLM_SFT_Qwen3_4B

4B • Updated Nov 2, 2025 • 8

Shiyu-Lab/Inputoutput_RL_Llama3_3B

4B • Updated Oct 29, 2025 • 4

Shiyu-Lab/HarnessLLM_RL_Llama3_3B

4B • Updated Oct 29, 2025 • 5

Shiyu-Lab/Inputoutput_RL_Qwen3_4B

4B • Updated Oct 29, 2025 • 4

Shiyu-Lab/HarnessLLM_RL_Qwen3_4B

4B • Updated Oct 13, 2025 • 4

Shiyu-Lab/QwQ-32B-thinkprune-iter2k

Text Generation • 33B • Updated Apr 23, 2025 • 26

Shiyu-Lab/DeepSeek-R1-Distill-Qwen-1.5B-thinkprune-3k

Text Generation • 2B • Updated Apr 8, 2025 • 14

datasets 15

Shiyu-Lab/Skill-Usage

Preview • Updated Apr 7 • 1.65k

Shiyu-Lab/WebArena_video_demo

Viewer • Updated Jan 20 • 3.69k • 40

Shiyu-Lab/OSWorld_video_demo

Preview • Updated Jan 20 • 44

Shiyu-Lab/Testcase_eval_data

Viewer • Updated Nov 10, 2025 • 215 • 29

Shiyu-Lab/Testcase_RL_Data

Viewer • Updated Nov 10, 2025 • 12k • 48

Shiyu-Lab/Inputoutput_SFT_Data

Viewer • Updated Nov 2, 2025 • 15.6k • 19

Shiyu-Lab/HarnessLLM_SFT_Data

Viewer • Updated Nov 2, 2025 • 15.6k • 20

Shiyu-Lab/Testcase_MBPPHard

Viewer • Updated Nov 2, 2025 • 141 • 15

Shiyu-Lab/Testcase_CF_Seen

Viewer • Updated Oct 13, 2025 • 100 • 12

Shiyu-Lab/Testcase_CF_Unseen

Viewer • Updated Oct 13, 2025 • 84 • 16

View 15 datasets