Multimodal & Generative AI 3: Generative Models & Diffusion
Thursday, November 26, 2026, – (Australia/Sydney)
Clarendon Room B · Conference
Paper 944 - WTDiff: High-Fidelity Weather Translation with One-Step Diffusion
Authors: Zixuan Hua, Xun Fang and Lihua Zhang
Paper 1069 - EmCom-Diffusion: Probing Visual Reflection in Emergent Languages via Image Generation
Authors: Haruumi Omoto and Tadahiro Taniguchi
Paper 1116 - Instance-Aware Conditioning for Specialized-Domain Generation
Authors: Suoxiang Zhang, Zhuoyan Hou, Zhonghong Wu, Hongrui Chang, Lifen Song and Ronghua Ji
Paper 1136 - PASTA: Prompt-Aware Shared-Latent Training-Free Annealed Diffusion Sampling
Authors: Ren Ajiki, Ryugo Morita, Stanislav Frolov, Brian B. Moser, Ko Watanabe, Riku Takahashi, Andreas Dengel and Jinjia Zhou
Paper 1275 - Phase Transition and Critical Phenomena in Learning in Generative Neural Nets - A case study through Music Generation
Authors: Rhea Paul and Shuichi Masuda
Paper 1385 - Trajectory-Aware Diffusion Scheduling: A Search-Based Framework for Training-Free Text-to-Video Generation
Authors: Yingda Yu, Jiaqi Xuan and Guanchao Tong
Paper 260 - Scale-Separated Conditioning for Style-Encoder-Free Diffusion Stylization
Authors: Jingtao Zhang, Haorui Gao, Youqing Liang and Zeming Liu
Paper 1363 - Think Before You Edit: Chain-of-Thought Image Editing via Video Trajectories
Authors: Yingda Yu, Jiaqi Xuan and Guanchao Tong