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
authored a paper about 4 hours ago
ThinkPrior: Zero-Rollout Difficulty Priors for Cold-Start Prompt Selection in RLVR authored a paper about 4 hours ago
BenchScope: How Many Independent Signals Does Your Benchmark Provide? authored a paper about 4 hours ago
GoAnt: Quality-Diversity Multi-Agent Search for Alpha Factor Discovery in Market Microstructure DataOrganizations
models 0
None public yet
datasets 13
Tommysha/octopus-train
Viewer • Updated • 1 • 96
Tommysha/zero-code-l1-cf-val
Viewer • Updated • 408 • 74 • 1
Tommysha/zero-code-l1-mbppplus-val
Viewer • Updated • 378 • 71
Tommysha/zero-code-l1-val
Viewer • Updated • 903 • 119
Tommysha/zero-code-l1-lcb-v5-test
Viewer • Updated • 279 • 258
Tommysha/zero-code-l1-cc-valid
Viewer • Updated • 117 • 64
Tommysha/zero-code-l1-lcb-v5-val
Viewer • Updated • 207 • 48
Tommysha/skillcenter-bundles
Updated • 411 • 1
Tommysha/goodhart-cascade-sweet-spot-14B
Viewer • Updated • 931 • 24
Tommysha/goodhart-cascade-sweet-spot-7B
Viewer • Updated • 1.34k • 37