Laser reformulates visual reasoning via Dynamic Windowed Alignment Learning to maintain latent superposition of global features, delivering 5.03% average gains over Monet and over 97% fewer inference tokens on six benchmarks.
arXiv preprint arXiv:2510.12603 (2025)
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
roles
baseline 1polarities
baseline 1representative citing papers
DMLR performs dynamic visual-textual interleaving in latent space using confidence-guided latent policy gradient optimization and a dynamic visual injection strategy, yielding improved multimodal reasoning on benchmarks.
Latent visual reasoning fails in current models because standard datasets make oracle latents uninformative and inference-time latents collapse away from useful representations.
citing papers explorer
-
Forest Before Trees: Latent Superposition for Efficient Visual Reasoning
Laser reformulates visual reasoning via Dynamic Windowed Alignment Learning to maintain latent superposition of global features, delivering 5.03% average gains over Monet and over 97% fewer inference tokens on six benchmarks.
-
Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Space
DMLR performs dynamic visual-textual interleaving in latent space using confidence-guided latent policy gradient optimization and a dynamic visual injection strategy, yielding improved multimodal reasoning on benchmarks.
-
What's Holding Back Latent Visual Reasoning?
Latent visual reasoning fails in current models because standard datasets make oracle latents uninformative and inference-time latents collapse away from useful representations.
- MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution