Xu Huang

Frontier multimodal models are beginning to predict future world states, but current benchmarks reveal vast performance disparities and highlight the critical role of underlying language model capabilities.

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.

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

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.

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.

LongCat-Next shatters the language-centric paradigm by unifying text, vision, and audio into a single autoregressive model with minimal modality-specific design, finally reconciling understanding and generation in discrete vision modeling.

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