16 33 169

Zhangchen Xu PRO

zhangchenxu

https://zhangchenxu.com/

AI & ML interests

LLM Data, Alignment, Post-Training, Safety

Recent Activity

authored a paper 4 days ago

VisualSphinx: Large-Scale Synthetic Vision Logic Puzzles for RL

updated a collection 4 days ago

VisualSphinx-V1

upvoted a paper 4 days ago

VisualSphinx: Large-Scale Synthetic Vision Logic Puzzles for RL

View all activity

Organizations

zhangchenxu's activity

authored a paper 4 days ago

VisualSphinx: Large-Scale Synthetic Vision Logic Puzzles for RL

Paper • 2505.23977 • Published 8 days ago • 9

updated a collection 4 days ago

VisualSphinx-V1

Collection

VisualSphinx-V1 is the largest fully-synthetic open-source dataset providing vision logic puzzles. • 7 items • Updated 4 days ago • 1

upvoted a paper 4 days ago

VisualSphinx: Large-Scale Synthetic Vision Logic Puzzles for RL

Paper • 2505.23977 • Published 8 days ago • 9

commented a paper 4 days ago

VisualSphinx: Large-Scale Synthetic Vision Logic Puzzles for RL

Paper • 2505.23977 • Published 8 days ago • 9 •

updated 2 models 4 days ago

VisualSphinx/VisualSphinx-Difficulty-Tagging

Updated 4 days ago • 6

zhangchenxu/Qwen2.5-Coder-7B-Instruct-taco_nosys-5k-llch_nosys-Vanilla-64-2N_step462

Updated 4 days ago • 66

published a model 4 days ago

zhangchenxu/Qwen2.5-Coder-7B-Instruct-taco_nosys-5k-llch_nosys-Vanilla-64-2N_step462

Updated 4 days ago • 66

updated a model 4 days ago

zhangchenxu/Qwen2.5-Coder-7B-Instruct-taco_nosys-5k-llch_nosys-Vanilla-64-2N_step256

Updated 4 days ago • 8

published a model 4 days ago

zhangchenxu/Qwen2.5-Coder-7B-Instruct-taco_nosys-5k-llch_nosys-Vanilla-64-2N_step256

Updated 4 days ago • 8

updated a model 4 days ago

zhangchenxu/Qwen2.5-Coder-7B-Instruct-taco_nosys-5k-llch_nosys-Vanilla-64-2N_step64

Updated 4 days ago • 8

published a model 4 days ago

zhangchenxu/Qwen2.5-Coder-7B-Instruct-taco_nosys-5k-llch_nosys-Vanilla-64-2N_step64

Updated 4 days ago • 8

liked 2 datasets 5 days ago

VisualSphinx/VisualSphinx-V1-Raw

Viewer • Updated 2 days ago • 662k • 559 • 2

VisualSphinx/VisualSphinx-V1-RL-20K

Viewer • Updated 2 days ago • 20k • 249 • 1

upvoted a paper 8 days ago

Personalized Safety in LLMs: A Benchmark and A Planning-Based Agent Approach

Paper • 2505.18882 • Published 13 days ago • 14

authored a paper 9 days ago

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

Paper • 2505.14625 • Published 18 days ago • 13

updated 2 datasets 9 days ago

zhangchenxu/HardVerify-Math

Viewer • Updated 9 days ago • 250 • 47

zhangchenxu/bigmath_tinyv_filtered

Viewer • Updated 9 days ago • 7.01k • 44

updated 2 models 9 days ago

zhangchenxu/TinyV-1.5B-Think

Text Generation • Updated 9 days ago • 45

zhangchenxu/TinyV-1.5B

Text Generation • Updated 9 days ago • 490

published a dataset 9 days ago

zhangchenxu/HardVerify-Math

Viewer • Updated 9 days ago • 250 • 47