Keyu Duan
vermouthdky
AI & ML interests
LLM Reasoning and Safety
Recent Activity
upvoted
a
paper
7 days ago
Efficient Process Reward Model Training via Active Learning
updated
a model
8 days ago
sail/ActPRM-X
updated
a model
8 days ago
sail/ActPRM
Organizations
Collections
2
models
6
vermouthdky/llama-3-70_unnatural_instruction_lima
Updated
•
1
vermouthdky/llama-3-70_natural_instruction_lima
Updated
vermouthdky/llama-3_unnatural_instruction_lima
Updated
vermouthdky/llama-3_natural_instruction_lima
Updated
vermouthdky/gemma-2_natural_instruction_lima
Updated
vermouthdky/gemma-2_unnatural_instruction_lima
Updated
•
2
datasets
6
vermouthdky/Unnatural_SimGSM8K
Viewer
•
Updated
•
100
•
25
vermouthdky/Unnatural_SynContextQA
Viewer
•
Updated
•
200
•
30
vermouthdky/Unnatural_LIMA
Viewer
•
Updated
•
1k
•
20
vermouthdky/prm800k-phase2
Viewer
•
Updated
•
491k
•
26
vermouthdky/prm800k-phase1
Viewer
•
Updated
•
30.9k
•
22
vermouthdky/SimTeG
Updated
•
37
•
1