The Token Replacement Test shows VLMs keep most accuracy gains even after corrupting or replacing continuous thought token content, indicating the tokens are not used as information bottlenecks.
SpatialSense: An adversarially crowdsourced benchmark for spatial rela- tion recognition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Ablate-to-Validate: Are Vision-Language Models Really Using Continuous Thought Tokens?
The Token Replacement Test shows VLMs keep most accuracy gains even after corrupting or replacing continuous thought token content, indicating the tokens are not used as information bottlenecks.