Lattice AI Research

Research focus

Code Generation & Program Synthesis (1)Eval Frameworks & Benchmarks (1)Tool Use & Agents (1)Data Curation & Synthetic Data (1)

Frequent co-authors

Junyang Lin (2)Bowen Wang (1)Dunjie Lu (1)Junli Wang (1)

Papers (2)

May 25, 2026

DAMOMay 25, 2026·also Tsinghua AI, HIT, HKU, SJTU

CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents

Forget hand-crafted benchmarks: CUA-Gym's auto-generated training data lets computer-use agents crush existing open-source models on real-world tasks.

Bowen Wang, Dunjie Lu, Junli Wang +10

Code Generation & Program Synthesis Eval Frameworks & Benchmarks Tool Use & Agents

Mar 17, 2026

Tsinghua AIMar 17, 2026·also DAMO

HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning

Multi-hop data synthesis using HopChain boosts VLM performance across a wide range of tasks, with gains of over 50 points in accuracy for ultra-long-context reasoning.

Shenzhi Wang, Shixuan Liu, Chang Gao +5

Data Curation & Synthetic Data Multimodal Models Reasoning & Chain-of-Thought

Search

Shixuan Liu

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)