Spotlight: Sphinx: Visual Perception and Reasoning Gym
Md Tanvirul Alam
Abstract
5-minute Spotlight presentations of the following papers:
Md Tanvirul Alam et al., Sphinx: Visual Perception and Reasoning Gym
Claas Beger et al., Investigating Abstraction Capabilities of the o3 Model Using Textual and Visual Modalities.
Qi Cao et al., DreamPRM: Domain-Reweighted Process Reward Model for Multimodal Reasoning.
Yamei Chen et al., Symbolic Graphics Programming with Large Language Models.
Video
Chat is not available.
Successful Page Load