arxiv:2510.02292
Shuyu Wu
wonderwind271
AI & ML interests
LLM (pre)training dynamics; Mechanistic Interpretability
Recent Activity
upvoted a paper about 22 hours ago
RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies published
a dataset 3 days ago
compling/rayzer-dl3dv-camera-tokens published
a dataset about 1 month ago
compling/event_factuality Organizations
models 16
wonderwind271/gpt2_scrub1
Text Generation • 0.1B • Updated
• 1
wonderwind271/gpt2-probe-finetune-UD-L4
Text Generation • 0.1B • Updated
• 1
wonderwind271/childes-checkpoints
Updated
wonderwind271/childes-probing-tunedlens
Updated
wonderwind271/vsdiag-checkpoints
Updated
wonderwind271/gpt2-vsdiag-1
Text Generation • 0.1B • Updated
wonderwind271/gpt2-childes-v4
Text Generation • 0.2B • Updated
wonderwind271/gpt2-childes-v2
Text Generation • 0.2B • Updated
• 1
wonderwind271/gpt2-childes-v1
Text Generation • 0.1B • Updated
• 1
wonderwind271/gpt2-ACL-series
Text Generation • 0.1B • Updated
datasets 18
wonderwind271/PKU-SafeRLHF-transformed
Viewer
• Updated
• 12k • 6
wonderwind271/en_gum-ud-train
Viewer
• Updated
• 7.79k • 12
wonderwind271/en_gum-ud-test
Viewer
• Updated
• 1.19k • 11
wonderwind271/en_gum-ud-dev
Viewer
• Updated
• 1.23k • 13
wonderwind271/en_ewt-ud-train
Viewer
• Updated
• 8.04k • 17
wonderwind271/en_ewt-ud-test
Viewer
• Updated
• 1.09k • 12
wonderwind271/en_ewt-ud-dev
Viewer
• Updated
• 1.03k • 11
wonderwind271/Hi-ToM
Viewer
• Updated
• 1.2k • 9
wonderwind271/wikipedia-selection-512w
Viewer
• Updated
• 940k • 13
wonderwind271/wikipedia-selection
Viewer
• Updated
• 1M • 10