HyLaR interleaves discrete text generation with continuous visual latent representations and optimizes them via a decoupled RL algorithm using vMF distributions, improving fine-grained visual reasoning.
In: The Thirteenth International Conference on Learning Representations (2025)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
Current video models succeed on basic understanding but achieve under 25% success on logically grounded generation and near 0% on interactive generation, exposing gaps in multimodal reasoning.
citing papers explorer
-
HyLaR: Hybrid Latent Reasoning with Decoupled Policy Optimization
HyLaR interleaves discrete text generation with continuous visual latent representations and optimizes them via a decoupled RL algorithm using vMF distributions, improving fine-grained visual reasoning.
-
How Far Are Video Models from True Multimodal Reasoning?
Current video models succeed on basic understanding but achieve under 25% success on logically grounded generation and near 0% on interactive generation, exposing gaps in multimodal reasoning.