Sohee Kim's picture

5

Sohee Kim

joyhee

AI & ML interests

None yet

Recent Activity

updated a dataset 2 days ago

joyhee/rl_scene-str

published a dataset 3 days ago

joyhee/rl_scene-str

updated a model 3 days ago

joyhee/NEW-easyr1-Qwen2.5-VL-7B-Instruct-RL-v6-blocks_s2_exp_s4_exp2_s5-length33-basic_ours-step55

View all activity

Organizations

None yet

upvoted a paper 3 months ago

When to Ensemble: Identifying Token-Level Points for Stable and Fast LLM Ensembling

Paper • 2510.15346 • Published Oct 17, 2025 • 34

upvoted 3 papers 4 months ago

Meta-Awareness Enhances Reasoning Models: Self-Alignment Reinforcement Learning

Paper • 2510.03259 • Published Sep 26, 2025 • 57

No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping

Paper • 2509.21880 • Published Sep 26, 2025 • 53

ReviewScore: Misinformed Peer Review Detection with Large Language Models

Paper • 2509.21679 • Published Sep 25, 2025 • 64

upvoted a paper 8 months ago

Reasoning Model is Stubborn: Diagnosing Instruction Overriding in Reasoning Models

Paper • 2505.17225 • Published May 22, 2025 • 64