Think Visually, Reason Textually: Vision-Language Synergy in ARC by Beichen Zhang

​Abstract: Abstract reasoning from minimal examples remains a core unsolved problem for frontier foundation models. The Abstraction and Reasoning Corpus (ARC-AGI) provides a rigorous testbed for this capability. We introduce two synergistic strategies: Vision-Language Synergy Reasoning (VLSR) and Modality-Switch Self-Correction (MSSC), yielding up to 4.33% improvement over text-only baselines.

​Speaker: Beichen Zhang — Researcher at Shanghai AI Laboratory, working on abstract reasoning, vision-language models, and artificial general intelligence.

​Website: https://journal.video-reason.com/ To join over zoom, please subscribe to get zoom link: https://forms.gle/ebgyvtLRz8ABTfdX6