Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
VIGOR: Benchmarking Visual Rationale Correctness in Multimodal Large Language Models
Yanlin Chen, Tang Li, Xi Peng
Multimodal large language models (MLLMs) are typically evaluated by whether they produce correct answers, but correctness alone does not reveal whether their outputs are supported…
cs.CV2026
"World Knowledge" in the Weights: Reading Concept Circuits of Vision Transformers
Yanlin Chen, Tang Li, Xi Peng
Vision transformers (ViTs) have achieved remarkable generalization across visual domains, yet little is known about how they internally represent the structure of the world. To add…