9 papers
GEAR: Guided End-to-End AutoRegression for Image Synthesis
Bin Lin, Zheyuan Liu, Chenguo Lin +8
Visual generative models are typically trained in two stages. A tokenizer is first trained for reconstruction and then frozen, after which a generator is trained on its discrete in…
ChronoPhyBench: Do MLLMs Truly Understand the World or Merely Exploit Language Priors?
Bin Zhu, Yanhao Jia, Kexin Zhao +12
Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated remarkable proficiency in open-world reasoning and understanding. However, a critical ambiguity pe…
OSP-Next: Efficient High-Quality Video Generation with Sparse Sequence Parallelism, HiF8 Quantization, and Reinforcement Learning
Yunyang Ge, Xianyi He, Zezhong Zhang +4
Diffusion Transformers achieve strong video generation quality, but the quadratic cost of full attention limits efficiency. We introduce OSP-Next, an efficient text-to-video genera…
iFSQ: Improving FSQ for Image Generation with 1 Line of Code
Bin Lin, Zongjian Li, Yuwei Niu +9
The field of image generation is currently bifurcated into autoregressive (AR) models operating on discrete tokens and diffusion models utilizing continuous latents. This divide, r…
FlashI2V: Fourier-Guided Latent Shifting Prevents Conditional Image Leakage in Image-to-Video Generation
Yunyang Ge, Xinhua Cheng, Chengshu Zhao +5
In Image-to-Video (I2V) generation, a video is created using an input image as the first-frame condition. Existing I2V methods concatenate the full information of the conditional i…
UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation
Bin Lin, Zongjian Li, Xinhua Cheng +9
Although existing unified models achieve strong performance in vision-language understanding and text-to-image generation, they remain limited in addressing image perception and ma…