Sohee Kim's picture

5

Sohee Kim

joyhee

AI & ML interests

None yet

Recent Activity

updated a model 26 minutes ago

joyhee/Qwen3-VL-4B-Instruct-RL-v6-blocks_s2_exp_s4_exp2_s5-basic-stepwise-new-step_26

published a model 28 minutes ago

joyhee/Qwen3-VL-4B-Instruct-RL-v6-blocks_s2_exp_s4_exp2_s5-basic-stepwise-new-step_26

updated a dataset about 2 hours ago

joyhee/rl_full_v6_tot_nobg-only_blocks-str

View all activity

Organizations

None yet

upvoted 2 papers 3 months ago

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

Paper • 2510.15346 • Published Oct 17, 2025 • 33

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

Paper • 2510.03259 • Published Sep 26, 2025 • 57

upvoted 2 papers 4 months ago

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

Paper • 2509.21880 • Published Sep 26, 2025 • 52

ReviewScore: Misinformed Peer Review Detection with Large Language Models

Paper • 2509.21679 • Published Sep 25, 2025 • 63

upvoted a paper 8 months ago

Reasoning Model is Stubborn: Diagnosing Instruction Overriding in Reasoning Models

Paper • 2505.17225 • Published May 22, 2025 • 64