Yankai Chen

Set representation models can be made robust to inference-time corruptions like outliers and missing data by training against a learned barycentric adversary.

LLMs can achieve more consistent and reliable cross-jurisdictional financial reporting by acting as constrained verifiers within a structured, agentic workflow, rather than as free-form generators.

LLM agents can now autonomously generate complex skills with multi-file dependencies, rivaling human-authored skills, thanks to a co-evolutionary verification process that doesn't need ground truth labels.

Diffusion language models can achieve better reasoning performance by explicitly balancing generation quality and exploration, outperforming methods that prioritize only one.

Even state-of-the-art LLMs struggle to adapt to mid-task changes in long-horizon web navigation, highlighting a critical gap in their ability to handle realistic user interactions.

Forget brute-force distillation: this method uses pedagogical principles to distill LLMs, boosting student model performance on complex reasoning tasks by up to 22.3%.