Schedule

Schedule

9:00 am - 9:10 am Introduction and Opening remarks 

9:10 am - 10:05 am Oral paper session (12 min talk + 3 min QA)

• End-to-End RAW Synergy for Elevated Vision-Language Reasoning

• Commonsense Storage Reasoning in Domestic Scenes: A Challenge for Vision-Language Models

• Representation Learning with Adaptive Superpixel Coding

• Multi-Modal Interpretability for Enhanced Localization in Vision-Language Models 

• Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Spatial Reasoning

10:05 am - 10:10 am Best Reviewer Award and Best Paper Award

10:10 am - 11:10 am Poster Session 

• MMDU-Bench: Multi-modal Deep Unlearning Benchmark

• Can Large Vision Language Models Understand Sarcasm?

• Ontology-Guided Prompting for Reasoning in Multimodal Vision-Language Models: An Application to Rare Dental Disease

• MET-Bench: Multimodal Entity Tracking for Evaluating the Limitations of Vision-Language and Reasoning Models

11:10 am - 12:10 pm Poster Session

• MemeBlip2: A Novel Light Weight Multimodal System to Detect Harmful Memes

• HueManity: Probing Fine-Grained Visual Perception in MLLMs

• GeoChain: Multimodal Chain-of-Thought for Geographic Reasoning

• ManeuverVLM: A Novel Multimodal Fusion of Scene Images and Temporal Signals for Maneuver Prediction

12:10 pm - 14:00 pm Lunch Break

14:00 pm - 14:45 pm Keynote by Professor Sai Rajeswar

14:45 pm - 15:30 pm Keynote by Professor Liang Zhao

15:30 pm - 16:00 pm End and Coffee Break