Fan Wang

Lumos-Nexus is a training-efficient framework that enhances video generation quality by progressively bridging generation from a lightweight model to a high-fidelity generator in a shared latent space, without sacrificing reasoning capabilities.

Lumos-Nexus is a training-efficient framework that enhances video generation quality by progressively bridging generation from a lightweight model to a high-fidelity generator in a shared latent space, without sacrificing reasoning capabilities.

The paper proposes a novel render-free framework that conditions video diffusion models directly on compressed 3D human mesh tokens, enabling robust 3D-aware human motion control without relying on rendered 2D guidance.

The paper proposes a novel render-free framework that conditions video diffusion models directly on compressed 3D human mesh tokens, enabling robust 3D-aware human motion control without relying on rendered 2D guidance.

WorldOlympiad is introduced as a benchmark for evaluating video-based world models across physical faithfulness, geometric consistency, and interaction fidelity.

The paper introduces ClinHallu, a benchmark for diagnosing and mitigating reasoning failures in medical multimodal large language models.

This paper introduces ClinFusion, a vision-centric multimodal large language model designed for holistic medical understanding, featuring a Cascade Spatial-Aware Locality Fusion operator and a vision-grounded evaluation framework.

The paper proposes BAMU, a framework for dynamic RVQ allocation in pretrained neural speech codecs, achieving consistent improvements on EnCodec and DAC.

The paper presents CoDA, a framework for co-evolving simulation data and an action policy to improve robot environment construction and policy learning.