arxiv:2510.02292
Shuyu Wu
wonderwind271
AI & ML interests
LLM (pre)training dynamics; Mechanistic Interpretability
Recent Activity
liked a model 2 days ago
openai/whisper-base updated a dataset 5 days ago
wonderwind271/speech-dataset published a dataset 5 days ago
wonderwind271/speech-datasetOrganizations
models 15
wonderwind271/gpt2-probe-finetune-UD-L4
Text Generation • 0.1B • Updated • 2
wonderwind271/childes-checkpoints
Updated
wonderwind271/childes-probing-tunedlens
Updated
wonderwind271/vsdiag-checkpoints
Updated
wonderwind271/gpt2-vsdiag-1
Text Generation • 0.1B • Updated • 2
wonderwind271/gpt2-childes-v4
Text Generation • 0.2B • Updated • 2
wonderwind271/gpt2-childes-v2
Text Generation • 0.2B • Updated
wonderwind271/gpt2-childes-v1
Text Generation • 0.1B • Updated • 1
wonderwind271/gpt2-ACL-series
Text Generation • 0.1B • Updated • 3
wonderwind271/wordlevel-tokenizer
Updated
datasets 19
wonderwind271/speech-dataset
Viewer • Updated • 19.7k • 42
wonderwind271/PKU-SafeRLHF-transformed
Viewer • Updated • 12k • 11
wonderwind271/en_gum-ud-train
Viewer • Updated • 7.79k • 5
wonderwind271/en_gum-ud-test
Viewer • Updated • 1.19k • 4
wonderwind271/en_gum-ud-dev
Viewer • Updated • 1.23k • 4
wonderwind271/en_ewt-ud-train
Viewer • Updated • 8.04k • 5
wonderwind271/en_ewt-ud-test
Viewer • Updated • 1.09k • 6
wonderwind271/en_ewt-ud-dev
Viewer • Updated • 1.03k • 6
wonderwind271/Hi-ToM
Viewer • Updated • 1.2k • 5
wonderwind271/wikipedia-selection-512w
Viewer • Updated • 940k • 5