Rex Ying

Performance gaps in multilingual medical evaluations reveal that proprietary models outperform open-source ones, but translation quality can swing results dramatically.

Task-oriented multi-agent systems can achieve unprecedented performance by leveraging specialized roles and subtasks, revealing the power of structured collaboration in AI.

Forgetting in hyperbolic continual learning is driven by semantic drift and hierarchical distortion, revealing critical insights for preserving multimodal representations.

Sparse user histories can be transformed into rich personalization insights by leveraging collaborative signals from behaviorally similar peers.

Rubric-Conditioned Self-Distillation transforms vague scalar rewards into precise, actionable feedback, leading to significant improvements in reasoning model performance.

MixTIME reveals that integrating diverse image modalities can significantly enhance the precision of immune biomarker predictions in oncology, outperforming traditional single-modality approaches.

LLMs' chain-of-thought reasoning often falls apart due to factual incompleteness, with errors compounding across multiple hops, as revealed by a new multi-hop QA dataset.