activity
20242026
collaborators

12 papers

cs.CV2026

Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling

Keming Wu, Zuhao Yang, Kaichen Zhang +24

Recent visual generation models have made major progress in photorealism, typography, instruction following, and interactive editing, yet they still struggle with spatial reasoning…

cs.CV2026

WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors

Keming Wu, Yijing Cui, Wenhan Xue +11

Commercial video generation systems such as Seedance2.0 and Veo3.1 have rapidly improved, strengthening the view that video generators may be evolving into "world simulators." Yet…

cs.CV2026

DiffSparse: Accelerating Diffusion Transformers with Learned Token Sparsity

Haowei Zhu, Ji Liu, Ziqiong Liu +4

Diffusion models demonstrate outstanding performance in image generation, but their multi-step inference mechanism requires immense computational cost. Previous works accelerate in…

cs.CV2026

Mango-GS: Enhancing Spatio-Temporal Consistency in Dynamic Scenes Reconstruction using Multi-Frame Node-Guided 4D Gaussian Splatting

Tingxuan Huang, Haowei Zhu, Jun-hai Yong +2

Reconstructing dynamic 3D scenes with photorealistic detail and strong temporal coherence remains a significant challenge. Existing Gaussian splatting approaches for dynamic scene…

cs.CV2026

TAP: A Token-Adaptive Predictor Framework for Training-Free Diffusion Acceleration

Haowei Zhu, Tingxuan Huang, Xing Wang +7

Diffusion models achieve strong generative performance but remain slow at inference due to the need for repeated full-model denoising passes. We present Token-Adaptive Predictor (T…

cs.CV2026

DiffBench Meets DiffAgent: End-to-End LLM-Driven Diffusion Acceleration Code Generation

Jiajun jiao, Haowei Zhu, Puyuan Yang +8

Diffusion models have achieved remarkable success in image and video generation. However, their inherently multiple step inference process imposes substantial computational overhea…