Yu-Jie Zhang

It is proved that symmetric losses enable successful policy improvement even with noisy labels, as the resulting reward is rank-preserving—a property that is identified as sufficient for policy improvement.

Degeneracy detection in LiDAR registration is not as stable as previously thought, with body-frame changes affecting up to 69.5% of label outputs.

LigBench transforms the landscape of LLM-driven research idea generation by providing a unified benchmark that aligns closely with expert evaluations.

A single click with SmellCC can eliminate 96.8% of Python code smells, transforming how developers manage technical debt.

Symmetry-aware abstention allows robots to avoid misidentifying their position in repetitive environments, achieving unprecedented accuracy in pose commitment.

OrthoPilot outperformed seasoned orthopaedic experts in diagnostic reasoning, achieving a 10.6% increase in management success for complex musculoskeletal cases.

XS-VLA outperforms larger models by leveraging spatial distillation and generative flow control, achieving remarkable efficiency in robotic manipulation.

ACE achieves a remarkable 70% success rate in constraint retrieval tasks without any task-specific retraining, showcasing the power of zero-shot workflow reasoning in robotic manipulation.

By integrating frequent directions matrix sketching, EOFD-MLogB slashes the computational costs of multinomial logistic bandits without sacrificing performance.

SkeMex enables medical agents to evolve their reasoning capabilities by transforming raw experience into structured, reusable skills, outperforming traditional memory systems.

Even with noisy human preferences, symmetric losses can guarantee rank-preserving rewards, unlocking robust policy optimization for aligning language models.