6 papers · 1 filter
MLLM-Guided Semantic Correction for Text-to-Video Generation
Junhao Chen, Zheqi Lv, Keting Yin +6
Recent advances in diffusion models and Transformer architectures have led to significant progress in text-to-video generation. However, these models often suffer from semantic err…
Training-Free Semantic Correction for Autoregressive Visual Models
Junhao Chen, Chanyu Zhu, Zheqi Lv +2
Autoregressive visual models (AVMs) based on next-scale prediction have emerged as a prominent paradigm for image and video synthesis. However, decomposing the generation process i…
The First Controllable Bokeh Rendering Challenge at NTIRE 2026
Tim Seizinger, Florin-Alexandru Vasluianu, Jeffrey Chen +23
This study presents the outcomes of the first Controllable Bokeh Rendering Challenge at NTIRE and highlights the most effective submitted methodologies. In total, 44 participants r…
MADFormer: Mixed Autoregressive and Diffusion Transformers for Continuous Image Generation
Junhao Chen, Yulia Tsvetkov, Xiaochuang Han
Recent progress in multimodal generation has increasingly combined autoregressive (AR) and diffusion-based approaches, leveraging their complementary strengths: AR models capture l…
Multimodal LLM-Guided Semantic Correction in Text-to-Image Diffusion
Zheqi Lv, Junhao Chen, Qi Tian +3
Diffusion models have become the mainstream architecture for text-to-image generation, achieving remarkable progress in visual quality and prompt controllability. However, current…
Varying Manifolds in Diffusion: From Time-varying Geometries to Visual Saliency
Junhao Chen, Manyi Li, Zherong Pan +2
Deep generative models learn the data distribution, which is concentrated on a low-dimensional manifold. The geometric analysis of distribution transformation provides a better und…