Multimodal & Generative AI 2: Vision-Language Models
Thursday, November 26, 2026, – (Australia/Sydney)
Clarendon Room B · Conference
Paper 113 - CoVR: Chain-of-Visual Reasoning for Multi-Turn Composed Image Retrieval
Authors: Wenjing Pang and Yin Chen
Paper 276 - LLM-Guided Degradation-Aware Road Scene Perception for Lane Detection and Foggy Object Detection (V)
Authors: Feng Yan and Dequan Zheng
Paper 1269 - Scene Structure Oriented Textual Inversion for Zero-Shot Composed Image Retrieval
Authors: Guo Tang and Huahu Xu
Paper 1355 - SAVOR: Self-Aware Visual Grounding via Confidence-Calibrated Reinforcement Learning for Multimodal Hallucination Mitigation
Authors: Zixiu Ding, Zilin Zhao, He Yingjie, Xinlang Kang, Guansu Wang and Wei Zhan
Paper 179 - InfoVLA: A Mid-Layer Information Bottleneck for Robust Vision-Language-Action Policies (V)
Authors: Ziming Liu, Qingxin Meng, Mingxuan Jing, Jin Zheng, Yuquan Wu and Linjuan Cheng
Paper 529 - PRCap: Pre-Enhancement and Noise-Robust Fusion for Retrieval-Augmented Image Captioning
Authors: Jianuo Han, Zihao Yu and Jun Sun
Paper 772 - HyperRES: A Prompt-Conditioned Hyperdecoder for Referring Expression Segmentation
Authors: Seung Yeop Ha, Jinhyeok Lee, Hyoseop Kim, Jun-Geol Baek and Hong-In Won
Paper 257 - ABDMural: Damage-Aware Brownian Bridge Diffusion for Mural Restoration
Authors: Sitong Ge, Ruofei Wang, Daohan Zhu, Honggu Chen, Yubo Hou, Tao Wan, Zengchang Qin and Zhongzhi Luan