-
LUFFY ★ PINNED
Official Repository of "Learning to Reason under Off-Policy Guidance"
Python ★ 460 3mo agoExplain → -
TPO ★ PINNED
Test-time preferenece optimization (ICML 2025).
Jupyter Notebook ★ 185 1y agoExplain → -
SU-01 ★ PINNED
SU-01: Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling
Python ★ 94 1mo agoExplain → -
Pi-Bench ★ PINNED
Benchmark for proactive personal assistant agents in long-horizon workflows.
Python ★ 55 1mo agoExplain → -
TRM ★ PINNED
Code repository for the ICML 2026 Oral paper "Characterizing, Evaluating, and Optimizing Complex Reasoning".
Python ★ 17 25d agoExplain → -
Draft-OPD
The official repo of "Draft-OPD: On-Policy Distillation for Speculative Draft Models"
Python ★ 50 8d agoExplain → -
ComBench
No description.
Python ★ 14 1d agoExplain →
No repos match these filters.