Xiao-Ming Wu

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Code Generation & Program Synthesis (1)Eval Frameworks & Benchmarks (1)Data Curation & Synthetic Data (1)Multimodal Models (1)

Frequent co-authors

Zaoyu Chen (1)Jianbo Dai (1)Boyu Zhu (1)Jingdong Wang (1)

Papers (2)

Apr 14, 2026

CodeSpecBench: Benchmarking LLMs for Executable Behavioral Specification Generation

LLMs that ace code generation often fail to grasp intended program semantics, as evidenced by a stark performance decline when generating executable behavioral specifications on the new CodeSpecBench benchmark.

Zaoyu Chen, Jianbo Dai, Boyu Zhu +6

Code Generation & Program Synthesis Eval Frameworks & Benchmarks

Mar 10, 2026

Mar 10, 2026·also CUHK

MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data

VLMs can now self-evolve from *zero* data, thanks to a multi-agent RL framework that synthesizes its own visual concepts and reasoning tasks.

Zongxia Li, Hongyang Du, Chengsong Huang +10

Data Curation & Synthetic Data Multimodal Models Tool Use & Agents

Search

Xiao-Ming Wu

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)