Chao Zhang

Achieve near-perfect speech recognition at a ridiculously low 200 bits per second by using reinforcement learning to directly optimize a neural codec for intelligibility.

Imagine creating high-fidelity, navigable 3D worlds from just a text prompt or a single image – HY-World 2.0 makes it a reality.

Attention Sink, where Transformers fixate on seemingly irrelevant tokens, is more than just a quirk – it's a fundamental challenge impacting training, inference, and even causing hallucinations, demanding a systematic approach to understanding and mitigating its effects.

Turns out, MLLMs struggle with manufacturing tasks not because they can't "see," but because they lack the domain-specific knowledge to understand what they're looking at.