3 papers
cs.CV2026
Seeing the Evidence, Missing the Answer: Tool-Guided Vision-Language Models on Visual Illusions
Xuesong Wang, Harry Wang
Vision-language models (VLMs) exhibit a systematic bias when confronted with classic optical illusions: they overwhelmingly predict the illusion as "real" regardless of whether the…
cs.CL2026
Story2Proposal: A Scaffold for Structured Scientific Paper Writing
Zhuoyang Qian, Wei Shi, Xu Lin +19
Generating scientific manuscripts requires maintaining alignment between narrative reasoning, experimental evidence, and visual artifacts across the document lifecycle. Existing la…
cs.LG2026
Humanity's Last Exam
Long Phan, Alice Gatti, Ziwen Han +1144
Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achi…