| Time Slot | Event | Speaker |
|---|---|---|
| 1:00 pm – 1:10 pm | Welcome and Opening Remarks | |
| 1:10 pm – 1:50 pm | 35 min Keynote + 5 min Q&A | |
| 1:50 pm – 2:30 pm |
Oral PresentationsMEBench: A Novel Benchmark for Understanding Mutual Exclusivity Bias in Vision-Language Models
Multimodal Graph-of-Thoughts: Hypothesis-Verification Graphs for Multimodal Reasoning in Vision-Language Models
Can Vision-Language Models Count? A Synthetic Benchmark and Analysis of Attention-Based Interventions
Relational Visual Similarity
|
4 x 10 min |
| 2:30 pm – 3:10 pm | 35 min Keynote + 5 min Q&A | |
| 3:10 pm – 3:30 pm | Break | |
| 3:30 pm – 4:10 pm | 35 min Keynote + 5 min Q&A | |
| 4:10 pm – 4:50 pm | 35 min Keynote + 5 min Q&A | |
| 4:50 pm – 5:00 pm | Closing Remarks + Awards | |
| 5:00 pm – 6:00 pm | Poster Session |
CogVL: Cognitive Foundations for Multimodal Models
CogVL Workshop @ CVPR 2026 brings together topics in vision, language, and cognitive science to move beyond surface-level intelligence toward models that reason, generalize, and decide reliably in the real world.
Schedule
Note: The schedule is subject to change.
Despite impressive perceptual and reasoning capabilities, vision-language models (VLMs) face challenges in systematic generalization, sample efficiency, commonsense reasoning, and trustworthy decision-making. The CogVL workshop provides a forum for researchers across computer vision, natural language processing, and cognitive science to explore how cognitively-inspired frameworks can address these limitations.
Our workshop is motivated by the emerging interest in whether cognitive principles such as counterfactual thinking, theory of mind, compositional reasoning, and causal inference can offer a blueprint for more adaptable, robust, and context-aware multimodal intelligence. Our half-day workshop features invited keynote talks, a panel discussion with leading experts, and selected papers. CogVL will also host the BlackSwan Challenge, which evaluates abductive reasoning (inferring hidden causes) and defeasible reasoning (adapting to new visual evidence) in unexpected video events.
Announcements
-
🚨 BlackSwan Challenge Deadline Extended! The BlackSwan Challenge deadline has been extended to May 1, 2026 (AoE)
(was April 15). See the submission details for more information. - 🚨 Deadline Extended! The paper submission deadline has been extended to March 6, 2026 (AoE).
-
Submission site is now open! Submit your papers via OpenReview. Deadline:
March 1, 2026March 6, 2026 (AoE). - The BlackSwan Challenge has launched! See the submission instructions page for details on how to participate.
- Follow us on X! CogVL Workshop on X
