Lattice AI Research

Research focus

RLHF & Preference Learning (2)Reasoning & Chain-of-Thought (1)Data Curation & Synthetic Data (1)Scalable Oversight & Alignment Theory (1)

Frequent co-authors

Zhenqing Ling (2)Daoyuan Chen (2)Qianli Shen (1)Yilun Huang (1)

Papers (2)

Aug 10, 2026

DAMO2w ago·also SYSU

Beyond Solvability: Task Learnability as a Static Prior for LLM RL Post-Training

Task learnability can significantly enhance RL efficiency in LLMs, leading to better performance with less data.

Ting Zhou, Zhenqing Ling, Daoyuan Chen +4

Reasoning & Chain-of-Thought RLHF & Preference Learning

Jun 25, 2026

Ting Zhou +3Jun 25, 2026

GEOALIGN: Geometric Rollout Curation for Robust LLM Reinforcement Learning

Directional inconsistency can destabilize LLM training, but geoalign curates rollouts to improve performance and stability, outperforming several established methods.

Ting Zhou, Zhenqing Ling, Yiyang Zhao +1

Data Curation & Synthetic Data RLHF & Preference Learning Scalable Oversight & Alignment Theory

Search

Ting Zhou

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)