conftrace_

Cong Qin

3 papers · 2026–2026 · 1 conference · across top CS/AI conferences

Conferences

ACL (3)

Top co-authors

Jiaye Lin (3) Yangyi Fang (3) Xiaoliang Fu (3) Ke Zeng (2) Lu Pan (2) Zekai Shao (2) Binbin Zheng (2) Chaowen Hu (2) Chang Liu (1) Haolin Shi (1)

Keywords

policy optimization (3) large language model (2) reinforcement learning (2) probability mass (1) probability gradient (1) gradient utilization (1) multi-turn optimization (1) importance sampling (1) credit assignment (1)

Papers

MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning ACL 2026 From log 𝜋 to 𝜋: Taming Divergence in Soft Clipping via Bilateral Decoupled Decay of Probability Gradient Weight ACL 2026 Proximity-Based Multi-Turn Optimization: Practical Credit Assignment for LLM Agent Training ACL 2026