Postdoc @LifeAtPurdue. Previously PhD @sjtu1896.
West Lafayette, IN
Joined May 2018
- Tweets10
- Following11
- Followers22
- Likes23
Excited to share MLS-Bench! Very fortunate to contribute ~20 tasks spanning trustworthy learning, structured & causal learning, and deep learning. I look forward to seeing how current AI agents will tackle and develop ML methods in these domains!
MLS-Bench has been accepted as an Oral at the NeurIPS 2026 E&D Track (15/3757)! It has also been featured in model releases from AI labs like Qwen.
MLS-Bench tests whether current Agents can invent ML methods that scale and generalize, the way human researchers have driven AI forward. It spans 140 tasks across 12 domains, with anti-hacking designs that isolate method invention from benchmark gaming.
We find that agents are much better at tuning existing methods than inventing new ones. They also lack the scientific judgment to plan experiments and test their own assumptions. Even the newest models, like Fable and Astra, plateau near existing human-designed methods.
📄 Paper: arxiv.org/abs/2605.08678
🏆 Leaderboard: mls-bench.com
💻 GitHub: github.com/Imbernoulli/MLS-B…
1
70
Our #NeurIPS2026 paper: Analytical Correction for Subsampling Bias in Drifting Models.
Minibatch drift is biased. ABC fixes it with 2 extra lines of code: bias O(1/n) → O(1/n²), lower FID & faster training. Try it!
📄 arxiv.org/abs/2604.27239
💻 github.com/lan-qing/Drifting…
Huge thanks to my amazing collaborators Zeyun Deng, Juanwu Lu, Ziran Wang, and @ruqi_zhang!
2
186
Jiaru Zhang retweeted
Everyone is talking about self-evolving AI, or recursive self-improvement. The methods that built modern ML are the ones that keep working across settings and scales, yet no benchmark directly tests AI systems for that ability.
Today, after months of cross-platform validation with external teams, we're proud to introduce MLS-Bench, a benchmark for ML Science with 140 tasks across 12 ML domains. It asks whether AI systems can create scalable and generalizable ML methods, the way human researchers have pushed AI forward. (1/9)
