CL Yu

clyu

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 1 day ago

Beyond the Verdict: Agentic Code Judging with Verifiable Feedback

liked a dataset 6 days ago

FineEnvs/openai-math

upvoted a paper 14 days ago

Training LLM Judges from Language Feedback via Position-Selective Self-Distillation

View all activity

Organizations

Papers 2

arxiv:2505.16421

arxiv:2505.16265

models 9

clyu/clip0.28_clipl0.2_vanilla_bsz512_mb128

Updated Dec 17, 2025

clyu/cliph4_clipl0.5_cumloss_bsz512_mb128

Updated Dec 17, 2025

clyu/qwen3_14b_rstar_sft_step802

15B • Updated Nov 17, 2025 • 11

clyu/mistral12b_skyworkllama8b_grpo_step180

12B • Updated Sep 7, 2025 • 10

clyu/mistral12b_skyworkllama8b_grpo_step160

12B • Updated Sep 7, 2025 • 12

clyu/mistral12b_skyworkllama8b_grpo_step120

12B • Updated Sep 6, 2025 • 10

clyu/mistral12b_skyworkllama8b_grpo_step80

12B • Updated Sep 6, 2025 • 10

clyu/Mixtral-8x22B-Instruct-v0.1-mcore

Updated May 23, 2025

clyu/Mixtral-8x7B-Instruct-v0.1-mcore

Updated Apr 24, 2025

datasets 2

clyu/sg_55k_cleaned_en_split8k

Viewer • Updated Mar 24, 2024 • 63k • 45

clyu/sg_55k_cleaned_en

Viewer • Updated Mar 24, 2024 • 79.2k • 37