2 papers
cs.AI2026
Does the Question Really Matter? Training-Free Data Selection for Vision-Language SFT
Peng Sun, Yi Yang, Huawen Shen +4
Visual instruction tuning is crucial for improving vision-language large models (VLLMs). However, many samples can be solved via linguistic patterns or common-sense shortcuts, with…
cs.CV2026
Decoding Scientific Experimental Images: The SPUR Benchmark for Perception, Understanding, and Reasoning
Junpeng Ding, Zichen Tang, Haihong E +17
We introduce SPUR, a comprehensive benchmark for scientific experimental image perception, understanding, and reasoning, comprising 4,264 question-answering (QA) pairs derived from…