Yichen Feng

yichen-f

·

AI & ML interests

LLM Data, Post-Training

Recent Activity

new activity 7 days ago

JobBench/job-bench:# Rubric validity: all-or-nothing criteria penalize correct deliverables on hidden/exact requirements (main split)

updated a dataset 13 days ago

JobBench/job-bench

new activity 16 days ago

JobBench/job-bench:Two scoring defects in JobBench dataset: omitted biostatistics exclusions and double-counted HPC power load

View all activity

Organizations

upvoted an article 7 months ago

Article

Visual Aesthetic Benchmark: Can Frontier Models Judge Beauty?

zhangchenxu

•

Feb 25

• 15

upvoted a paper 8 months ago

Think3D: Thinking with Space for Spatial Reasoning

Paper • 2601.13029 • Published Jan 19 • 48

upvoted a paper over 1 year ago

VisualSphinx: Large-Scale Synthetic Vision Logic Puzzles for RL

Paper • 2505.23977 • Published May 29, 2025 • 10

upvoted a collection over 1 year ago

VisualSphinx-V1

VisualSphinx-V1 is the largest fully-synthetic open-source dataset providing vision logic puzzles. • 7 items • Updated Jun 3, 2025 • 1

upvoted a paper over 1 year ago

TinyV: Reducing False Negatives in Verification Improves RL for LLM Reasoning

Paper • 2505.14625 • Published May 20, 2025 • 13