2 papers
cs.CL2026
Where MLLMs Fail and Why: Causal Task Decomposition for Capability Failure Diagnosis
Xia Hu, Brian Potetz, Chun-Ta Lu +6
End-to-end accuracy on compositional tasks records how often MLLMs fail, but cannot distinguish whether a failure reflects an intrinsic deficit in the targeted capability or a casc…
cs.CV2026
The Cartesian Shortcut: Re-evaluate Vision Reasoning in Polar Coordinate Space
Xia Hu, Zhenrui Yue, Brian Potetz +4
As current Multimodal Large Language Models rapidly saturate canonical visual reasoning benchmarks, a key question emerges: do these strong scores genuinely reflect robust visual u…