Zhiheng Wang

@zhiheng-wang · 1 works

Recent posts by Zhiheng Wang

• The Illusion of Visual Tool-Use: A Causal Audit of Thinking with Images - The "thinking-with-images" paradigm equips multimodal LLMs with active visual operations such as crop-and-zoom. However, models using these operations often achieve only marginal or negative gains… · Paper · arxiv.org