Xu Huang

A unified architecture achieves SOTA embodied AI by jointly learning physical reasoning, world generation, and action prediction, outperforming prior models in generalization and long-horizon tasks.

State-of-the-art VLMs struggle to execute scientific research workflows, revealing a critical gap in their ability to interact with specialized software and produce verifiable results.

A novel decoupled autoencoder design unlocks 32x spatial compression for diffusion models while simultaneously boosting reconstruction fidelity and accelerating training convergence.

AutoDesign outperforms existing design systems by aligning with human design principles and achieving superior poster generation quality through recursive self-improvement.

Executable Blender code transforms text-to-video generation, enabling unprecedented control over scene dynamics and visual fidelity.

Transforming fragmented XAS data into a structured dataset unlocks unprecedented opportunities for high-throughput material discovery in battery research.

Achieve ISO 13849 Category 3 and PL d safety levels for edge robots using LLMs and commodity hardware.

Fine-tuning smaller reasoning models on data from larger models can backfire spectacularly unless you carefully match the stylistic nuances of the student.