arxiv:2609.09075
Tianming (Tommy) Sha
Tommysha
·
AI & ML interests
LLM Post-Training, Agentic RL, Multi-Agent Systems, LLM Serving & KV Cache Systems (Octopus)
Recent Activity
liked a model 3 days ago
Tommysha/Octopus-Qwen3.5-4B updated a model 3 days ago
Tommysha/Octopus-Qwen3.5-4B published a model 6 days ago
Tommysha/Octopus-Qwen3.5-4BOrganizations
datasets 13
Tommysha/octopus-train
Viewer • Updated • 1 • 149
Tommysha/zero-code-l1-cf-val
Viewer • Updated • 408 • 79 • 1
Tommysha/zero-code-l1-mbppplus-val
Viewer • Updated • 378 • 77
Tommysha/zero-code-l1-val
Viewer • Updated • 903 • 140
Tommysha/zero-code-l1-lcb-v5-test
Viewer • Updated • 279 • 329
Tommysha/zero-code-l1-cc-valid
Viewer • Updated • 117 • 76
Tommysha/zero-code-l1-lcb-v5-val
Viewer • Updated • 207 • 75
Tommysha/skillcenter-bundles
Updated • 518 • 1
Tommysha/goodhart-cascade-sweet-spot-14B
Viewer • Updated • 931 • 35
Tommysha/goodhart-cascade-sweet-spot-7B
Viewer • Updated • 1.34k • 38