Sohyun An
sohyunan
AI & ML interests
None yet
Recent Activity
upvoted a paper about 2 months ago
AutoRubric-T2I: Robust Rule-Based Reward Model for Text-to-Image Alignment upvoted a paper 3 months ago
T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary SearchOrganizations
models 16
sohyunan/DeepSeek-R1-Distill-Qwen-1.5B-sft-lora
Updated
sohyunan/DeepSeek-R1-Distill-Qwen-1.5B-sft-full
Updated
sohyunan/gemma-2-2b-it-maze-sft-sys0.0
Text Generation • 3B • Updated • 17 •
sohyunan/gemma-2-2b-it-maze-sft-ctrl-sys0.5-a_star
Text Generation • 3B • Updated • 15 •
sohyunan/gemma-2-2b-it-maze-sft-sys1.0-a_star
Text Generation • 3B • Updated • 5
sohyunan/gemma-2-2b-it_controller_sft_random_grpo
Text Generation • 3B • Updated • 3
sohyunan/debug
Text Generation • Updated • 5
sohyunan/gemma-2-2b-it_controller_sft_random_grpo_lora
Updated
sohyunan/gemma-2-2b-it_controller_grpo_lora
Updated
sohyunan/gemma-2-2b-it_controller_sft_random
Text Generation • 3B • Updated • 5
datasets 0
None public yet