arxiv:2609.39687
Tom Lu
eigentom
AI & ML interests
MLLM, Reinforcement Learning, Agentic RL
Recent Activity
updated a dataset about 9 hours ago
eigentom/minicpm5-swe-native-eval-archive published a dataset about 17 hours ago
eigentom/minicpm5-swe-native-eval-archive authored a paper about 24 hours ago
Better Supervision Is Nearby: Neighborhood On-Policy Self-DistillationOrganizations
datasets 7
eigentom/minicpm5-swe-native-eval-archive
Viewer • Updated • 2.2k
eigentom/minicpm5-sft-swe-validation-200
Viewer • Updated • 200 • 51
eigentom/minicpm5-sft-stage1-910c-pub
Viewer • Updated • 1.76M • 55
eigentom/qwen35-4b-dci-rl-rewardv2-step10-bcp100-eval
Updated • 21
eigentom/qwen35-9b-sft-consolidated-sources-20260709
Viewer • Updated • 5.41k • 5
eigentom/ti_coding_agent_training_probe_20260624
Viewer • Updated • 11.5k • 127
eigentom/reformatted_deepreview
Viewer • Updated • 27k