Xu Wang

Vidu S2, which comprises Vidu S2-Avatar, a real-time interactive digital-character model, and Vidu S2-Editing, a real-time video editing model, is presented and the feasibility of real-time spatial video generation for both Vidu S2-Avatar and Vidu S2-Editing is explored.

Optimizing GPU resource allocation can cut multi-agent workflow completion times by nearly 37% while saving substantial GPU usage.

Achieving state-of-the-art segmentation accuracy without any training, VCAR tackles the critical issues of viewpoint coverage and boundary artifacts in 3D Gaussian Splatting.

Achieving up to 49.4% faster computations for neutron diffusion problems without sacrificing accuracy could revolutionize reactor core analysis.

VideoRover unifies video reasoning and external knowledge retrieval, achieving competitive performance with fewer resources than larger models.

Transferring frozen memory between models can yield substantial performance gains, but only if the target model's reader is properly aligned.

HUGIN boosts vision-language model accuracy for logistics sorting by over 15 percentage points, showcasing a significant leap in performance through innovative training techniques.

Motion-as-Prompt reveals that enhancing motion reasoning in MLLMs can lead to substantial accuracy gains without altering model architecture or requiring retraining.

Teacher-student mismatch can lead to flawed outputs, but TIDE's innovative correction method boosts reasoning accuracy by over 200% in challenging scenarios.

Local Margin Restoration not only shields VLMs from bias but also preserves their semantic integrity, leading to superior performance in dynamic environments.

Voice-controlled video generation just got a major upgrade with Vidu S1, achieving real-time performance without visual distortion.