5 papers
Uni-MMMU: A Massive Multi-discipline Multimodal Unified Benchmark
Kai Zou, Ziqi Huang, Yuhao Dong +7
Unified multimodal models aim to jointly enable visual understanding and generation, yet current benchmarks rarely examine their true integration. Existing evaluations either treat…
EchoGen: Cycle-Consistent Learning for Unified Layout-Image Generation and Understanding
Kai Zou, Hongbo Liu, Dian Zheng +3
In this work, we present EchoGen, a unified framework for layout-to-image generation and image grounding, capable of generating images with accurate layouts and high fidelity to te…
HiAR: Efficient Autoregressive Long Video Generation via Hierarchical Denoising
Kai Zou, Dian Zheng, Hongbo Liu +3
Autoregressive (AR) diffusion offers a promising framework for generating videos of theoretically infinite length. However, a major challenge is maintaining temporal continuity whi…
VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness
Dian Zheng, Ziqi Huang, Hongbo Liu +9
Video generation has advanced significantly, evolving from producing unrealistic outputs to generating videos that appear visually convincing and temporally coherent. To evaluate t…
ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models
Hongbo Liu, Jingwen He, Yi Jin +11
Cinematography, the fundamental visual language of film, is essential for conveying narrative, emotion, and aesthetic quality. While recent Vision-Language Models (VLMs) demonstrat…