Workshop
New Frontiers in Visual Language Reasoning: Compositionality, Prompts and Causality
Ziliang Chen · Vicente Ordonez · Guangrun Wang · Hao Wang · Tianlu Wang · Xiaodan Liang · Liang Lin · Alan Yuille
East 9
Sun 18 Jun, 9:15 a.m. PDT
Keywords: Vision+language
Recent years have seen the stunning powers of Visual Language Pre-training (VLP) models. Although VLPs have revolutionalized some fundamental principles of visual language reasoning (VLR), the other remaining problems prevent them from “thinking” like a human being: how to reason the world from breaking into parts (compositionality), how to achieve the generalization towards novel concepts provided a glimpse of demonstrations in context (prompts), and how to debias visual language reasoning by imagining what would have happened in the counterfactual scenarios (causality).
The workshop provides the opportunity to gather researchers from different fields to review the technology trends of the three lines, to better endow VLPs with these reasoning abilities. Our workshop also consists of two multi-modal reasoning challenges under the backgrounds of cross-modal math-word calculation and proving problems. The challenges are practical and highly involved with our issues, therefore, shedding more insights into the new frontiers of visual language reasoning.
Schedule
Sun 9:30 a.m. - 10:15 a.m.
|
Hanwang Zhang, National University of Sing ( Presentation ) > link | 🔗 |
Sun 10:15 a.m. - 11:00 a.m.
|
Elias Bareinboim, Columbia University ( Presentation ) > link | 🔗 |
Sun 11:00 a.m. - 11:45 a.m.
|
Anna Rohrbach, UC Berkeley ( Presentation ) > link | 🔗 |
Sun 11:45 a.m. - 12:30 p.m.
|
Zeynep Akata, Universtität Tübingen ( Presentation ) > link | 🔗 |
Sun 2:15 p.m. - 3:00 p.m.
|
Alan Yuille, Johns Hopkins, "Visual-Language Models: An Analysis By Synthesis Perspective" ( Presentation ) > link | 🔗 |
Sun 3:00 p.m. - 3:45 p.m.
|
Ziwei Liu, Nanyant Technological University, "Towards Building a Practical AI Assistant" ( Presentation ) > link | 🔗 |
Sun 3:45 p.m. - 4:30 p.m.
|
Ranjay Krishna, University of Washington, "Vision-language compositionality" ( Presentation ) > link | 🔗 |