TRANSPORTER generates videos from VLM logits using optimal transport to interpret model predictions on object attributes, actions, and scenes.
Beyond concept bottleneck models: How to make black boxes intervenable?NeurIPS, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
TRANSPORTER: Transferring Visual Semantics from VLM Manifolds
TRANSPORTER generates videos from VLM logits using optimal transport to interpret model predictions on object attributes, actions, and scenes.