DRIFT adapts pretrained VLMs to continuous decoding via a base predictor plus residual flow matching, outperforming regression and generative baselines on grounding and robotic control tasks.
Valley: Video assistant with large language model enhanced ability
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
-
DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models
DRIFT adapts pretrained VLMs to continuous decoding via a base predictor plus residual flow matching, outperforming regression and generative baselines on grounding and robotic control tasks.