MLLMs drop from over 85% accuracy on action presence to under 50% on matched action-denial videos, exposing a causal verification gap that causal graph prompts partially close.
Something Something
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
TimeProVe proposes a propose-then-verify framework using lightweight action-based candidate evidence generation followed by targeted VLM verification for efficient long video temporal reasoning, achieving 7.3% improvement on OTB with 75% fewer VLM calls.
Introduces CausalPhys benchmark with causal graphs and CRFT fine-tuning to improve VLMs' causal physical reasoning accuracy and interpretability.
The survey frames VLA models as pipelines that generate progressively grounded action tokens and classifies those tokens into eight types to guide future development.
citing papers explorer
-
A Survey on Vision-Language-Action Models: An Action Tokenization Perspective
The survey frames VLA models as pipelines that generate progressively grounded action tokens and classifies those tokens into eight types to guide future development.