collaborators

10 papers

cs.CV2026

Memento: Reconstruct to Remember for Consistent Long Video Generation

Xuan Wei, Longbin Ji, Guan Wang +5

Long-form video generation requires recurring subjects to remain consistent across various shots, viewpoints, motions, and scene transitions. Existing temporal decomposition method…

cs.CV2026

Native Audio-Visual Alignment for Generation

Longbin Ji, Guan Wang, Xuan Wei +6

Joint audio-video generation aims to synthesize temporally synchronized and semantically coherent visual-acoustic content. However, existing open-source methods mainly rely on eith…

cs.CV2026

Blink: Dynamic Visual Token Resolution for Enhanced Multimodal Understanding

Yuchen Feng, Zhenyu Zhang, Naibin Gu +8

Multimodal large language models (MLLMs) have achieved remarkable progress on various vision-language tasks, yet their visual perception remains limited. Humans, in comparison, per…

cs.CL2026

Elastic MoE: Unlocking the Inference-Time Scalability of Mixture-of-Experts

Naibin Gu, Zhenyu Zhang, Yuchen Feng +8

Mixture-of-Experts (MoE) models typically fix the number of activated experts at both training and inference. However, real-world deployments often face heterogeneous hardware,…

cs.CL2026

Sparse Growing Transformer: Training-Time Sparse Depth Allocation via Progressive Attention Looping

Yao Chen, Yilong Chen, Yinqi Yang +9

Existing approaches to increasing the effective depth of Transformers predominantly rely on parameter reuse, extending computation through recursive execution. Under this paradigm,…

cs.LG2026

Mixture of Universal Experts: Scaling Virtual Width via Depth-Width Transformation

Yilong Chen, Naibin Gu, Junyuan Shang +8

Mixture-of-Experts (MoE) decouples model capacity from per-token computation, yet their scalability remains limited by the physical dimensions of depth and width. To overcome this,…