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.
Forest Before Trees: Latent Superposition for Efficient Visual Reasoning
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
abstract
While Chain-of-Thought empowers Large Vision-Language Models with multi-step reasoning, explicit textual rationales suffer from an information bandwidth bottleneck, where continuous visual details are discarded during discrete tokenization. Recent latent reasoning methods attempt to address this challenge, but often fall prey to premature semantic collapse due to rigid autoregressive objectives. In this paper, we propose Laser, a novel paradigm that reformulates visual deduction via Dynamic Windowed Alignment Learning (DWAL). Instead of forcing a point-wise prediction, Laser aligns the latent state with a dynamic validity window of future semantics. This mechanism enforces a "Forest-before-Trees" cognitive hierarchy, enabling the model to maintain a probabilistic superposition of global features before narrowing down to local details. Crucially, Laser maintains interpretability via decodable trajectories while stabilizing unconstrained learning via Self-Refined Superposition. Extensive experiments on 6 benchmarks demonstrate that Laser achieves state-of-the-art performance among latent reasoning methods, surpassing the strong baseline Monet by 5.03% on average. Notably, it achieves these gains with extreme efficiency, reducing inference tokens by more than 97%, while demonstrating robust generalization to out-of-distribution domains.
citation-role summary
background 1
baseline 1
citation-polarity summary
fields
cs.CV 4years
2026 4representative citing papers
Latent diffusion models exhibit geometric decoupling where curvature in out-of-distribution generation is misallocated to unstable semantic boundaries instead of image details, identifying geometric hotspots as the structural cause of editing instability.
Visual replay module and adaptive depth scaling improve multimodal latent reasoning, reaching SOTA benchmarks with faster inference than explicit chain-of-thought methods.
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
-
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.
-
Geometric Decoupling: Diagnosing the Structural Instability of Latent
Latent diffusion models exhibit geometric decoupling where curvature in out-of-distribution generation is misallocated to unstable semantic boundaries instead of image details, identifying geometric hotspots as the structural cause of editing instability.
-
Visual Enhanced Depth Scaling for Multimodal Latent Reasoning
Visual replay module and adaptive depth scaling improve multimodal latent reasoning, reaching SOTA benchmarks with faster inference than explicit chain-of-thought methods.
-
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.