Kang Chen

Achiral active matter spontaneously generates reversible nonreciprocity by coupling deformation to rotation, bypassing the need for inherent chirality or external driving.

Standard SGD can get arbitrarily close to an anytime convergence rate of $\sqrt{\log n / n}$, but hitting that benchmark exactly is mathematically impossible under any deterministic step-size schedule.

Routing-guided exploration boosts software fix resolution rates by nearly 8%, outperforming traditional sampling methods without needing explicit answer forms.

J64 reveals hidden reasoning states that can significantly boost model accuracy and decision-making, while R64 provides a lightweight, effective proxy for deployment.

Current attention mechanisms misjudge the relevance of visual information, risking the loss of crucial context in multimodal dialog systems.

STEAM redefines how robots learn from mixed-quality data, achieving up to 59% higher success rates in real-world tasks by effectively identifying reliable progress.

Identical token IDs in sparse MoE models can lead to different expert outputs, revealing a nuanced structure that enhances reasoning control through innovative routing techniques.

LaWAM achieves up to 24x lower latency than traditional pixel-space models while maintaining state-of-the-art performance in robot control tasks.

Forget static datasets – RL-based co-training unlocks +20% real-world VLA performance by interactively leveraging simulation while preserving real-world capabilities.