7 papers
HarnessEval-W: Agentifying the Evaluation of Visual Worlds
Weiliang Chen, Haowen Sun, Jun Gao +40
A benchmark should deliver more than a scalar score: what makes an evaluation trustworthy is the reasoning that justifies the score. This is especially critical for world models, w…
Spatial-Aware Reduction Framework: Towards Efficient and Faithful Visual State Space Models
Jindi Lv, Aoyu Li, Yuhao Zhou +6
Mamba demonstrates strong efficiency in modeling long visual sequences. However, when token reduction is applied to structurally enhanced Mamba variants, these models exhibit a sev…
TivTok: Broadcasting Time-Invariant Tokens for Scalable Video Tokenization
Weiliang Chen, Yuanhui Huang, Xuebo Wang +1
Video tokenization is fundamental to scalable video generation, as the number of tokens directly determines the computational cost and the length of videos that can be modeled. Exi…
MBench: A Comprehensive Benchmark on Memory Capability for Video World Models
Shengjun Zhang, Zhang Zhang, Simin Huang +11
Recent advancements in video-based world models have demonstrated an unprecedented ability to synthesize high-fidelity visual sequences. However, a fundamental gap persists between…
RhymeFlow: Training-Free Acceleration for Video Generation with Asynchronous Denoising Flow Scheduling
Chensheng Dai, Shengjun Zhang, Yifan Li +3
Video generation models based on Diffusion Transformers (DiTs) have achieved remarkable performance in video synthesis, yet they suffer from high inference latency and computationa…
SurfelSplat: Learning Efficient and Generalizable Gaussian Surfel Representations for Sparse-View Surface Reconstruction
Chensheng Dai, Shengjun Zhang, Min Chen +1
3D Gaussian Splatting (3DGS) has demonstrated impressive performance in 3D scene reconstruction. Beyond novel view synthesis, it shows great potential for multi-view surface recons…