|
Poster
|
Tue 7:30
|
COSA: Concatenated Sample Pretrained Vision-Language Foundation Model
Sihan Chen · Xingjian He · Handong Li · Xiaojie Jin · Jiashi Feng · Jing Liu
|
|
|
Workshop
|
|
Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Representation Learning
Simon Schrodi · David Hoffmann · Max Argus · Volker Fischer · Thomas Brox
|
|
|
Workshop
|
|
Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Representation Learning
Simon Schrodi · David Hoffmann · Max Argus · Volker Fischer · Thomas Brox
|
|
|
Poster
|
Wed 7:30
|
Faithful Vision-Language Interpretation via Concept Bottleneck Models
Songning Lai · Lijie Hu · Junxiao Wang · Laure Berti-Equille · Di Wang
|
|
|
Poster
|
Tue 1:45
|
Measuring Vision-Language STEM Skills of Neural Models
Jianhao Shen · Ye Yuan · Srbuhi Mirzoyan · Ming Zhang · Chenguang Wang
|
|
|
Poster
|
Tue 1:45
|
Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models
Archiki Prasad · Elias Stengel-Eskin · Mohit Bansal
|
|
|
Poster
|
Thu 7:30
|
MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models
Deyao Zhu · jun chen · Xiaoqian Shen · Xiang Li · Mohamed Elhoseiny
|
|
|
Workshop
|
|
Sparkles: Unlocking Chats Across Multiple Images for Multimodal Instruction-Following Models
Yupan Huang · Zaiqiao Meng · Fangyu Liu · Yixuan Su · Nigel Collier · Yutong Lu
|
|
|
Poster
|
Wed 1:45
|
Improved baselines for vision-language pre-training
Jakob Verbeek · Enrico Fini · Michal Drozdzal · Pietro Astolfi · Adriana Romero-Soriano
|
|
|
Poster
|
Wed 7:30
|
An Image Is Worth 1000 Lies: Transferability of Adversarial Images across Prompts on Vision-Language Models
Haochen Luo · Jindong Gu · Fengyuan Liu · Philip Torr
|
|
|
Poster
|
Wed 7:30
|
Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models
Shuai Zhao · Xiaohan Wang · Linchao Zhu · Yi Yang
|
|
|
Poster
|
Fri 7:30
|
Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning
Juan Rocamonde · Victoriano Montesinos · Elvis Nava · Ethan Perez · David Lindner
|
|
