Tom Lu

eigentom

·

https://eigentom.github.io

EigenTom

AI & ML interests

MLLM, Reinforcement Learning, Agentic RL

Recent Activity

upvoted a paper 2 days ago

MemTrain: Self-Supervised Context Memory Training

upvoted a paper 3 days ago

Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement

published a model 21 days ago

eigentom/qwen35-4b-dci-rl-rewardv2-step10

View all activity

Organizations

Papers 12

arxiv:2606.14885

arxiv:2605.05242

arxiv:2604.08523

arxiv:2603.16124

models 1

eigentom/qwen35-4b-dci-rl-rewardv2-step10

Text Generation • Updated Jul 29 • 4

datasets 4

eigentom/qwen35-4b-dci-rl-rewardv2-step10-bcp100-eval

Updated Jul 29 • 51

eigentom/qwen35-9b-sft-consolidated-sources-20260709

Viewer • Updated Jul 9 • 5.41k • 3

eigentom/ti_coding_agent_training_probe_20260624

Viewer • Updated Jun 24 • 11.5k • 521

eigentom/reformatted_deepreview

Viewer • Updated Nov 25, 2025 • 27k • 2