Lichang Chen

Lichang-Chen's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

updated a dataset 3 days ago

Lichang-Chen/omnixR-data

Viewer • Updated 3 days ago • 1.4k • 1

updated 2 models 10 days ago

Lichang-Chen/llama-8b-gemini-point60-100-wo-cot

Text Generation • Updated 10 days ago • 67

Lichang-Chen/llama-8b-gemini-point21-60-wo-cot

Text Generation • Updated 10 days ago • 45

updated a model 14 days ago

Lichang-Chen/llama-8b-gemini-point21-60_shuffle

Text Generation • Updated 14 days ago • 49

updated 2 models 15 days ago

Lichang-Chen/llama-8b-gemini-point21-60

Text Generation • Updated 15 days ago • 51

Lichang-Chen/llama-8b-gemini-point60-100

Text Generation • Updated 15 days ago • 61

updated a model 24 days ago

Lichang-Chen/llama3-8b-point60-100

Text Generation • Updated 24 days ago • 104

updated 6 models about 1 month ago

Lichang-Chen/llama3-8b-point21-100

Text Generation • Updated Oct 23 • 5

Lichang-Chen/llama3-8b-point21-60

Text Generation • Updated Oct 23 • 62

Lichang-Chen/llama3-8b-point27-template

Text Generation • Updated Oct 18 • 6

Lichang-Chen/llama3-8b-point22-template

Text Generation • Updated Oct 18 • 6

Lichang-Chen/llama3-8b-point27

Text Generation • Updated Oct 17 • 6

Lichang-Chen/llama3-8b-point22

Text Generation • Updated Oct 17 • 6

authored a paper 2 months ago

RRM: Robust Reward Model Training Mitigates Reward Hacking

Paper • 2409.13156 • Published Sep 20 • 3

upvoted a paper 2 months ago

RRM: Robust Reward Model Training Mitigates Reward Hacking

Paper • 2409.13156 • Published Sep 20 • 3

updated 2 models 2 months ago

Lichang-Chen/llama3_sft_unbiased_iter1

Updated Sep 20

Lichang-Chen/llama3_it_odin_bold_attack

Feature Extraction • Updated Sep 20 • 3

updated 3 datasets 2 months ago

Lichang-Chen/llama_sft_dpo_bold_list_attack_eval_iter3

Viewer • Updated Sep 18 • 800 • 30

Lichang-Chen/llama_sft_dpo_bold_list_attack_eval_iter2

Viewer • Updated Sep 18 • 800 • 34

Lichang-Chen/llama_sft_dpo_bold_list_attack_iter1

Viewer • Updated Sep 18 • 800 • 37