DLR is proposed, a reinforced latent reasoning framework that dynamically decomposes queries into textual premises, extracts premise-conditioned continuous visual latents, and deduces answers through grounded rationales to enable effective exploration in the latent space.
Abstract
Vision-Language Models often struggle with complex visual reasoning due to the visual information loss in textual CoT. Existing methods either add the cost of tool calls or rely on localized patch-based embeddings that are insufficient to extract semantics in multi-step reasoning. We propose"Decompose, Look, and Reason"(DLR), a reinforced latent reasoning framework that dynamically decomposes queries into textual premises, extracts premise-conditioned continuous visual latents, and deduces answers through grounded rationales. We introduce a three-stage training pipeline and propose a novel Spherical Gaussian Latent Policy, to enable effective exploration in the latent space. Extensive experiments on vision-centric benchmarks show that DLR consistently outperforms strong baselines, including text-only, interleaved multimodal CoT, and latent reasoning methods, while providing superior stepwise interpretability.
LARK (Latent-Aligned Reasoning frameworK), a two-stage latent reasoning framework with complementary alignment mechanisms within a single VLM, achieves state-of-the-art performance across multiple recommendation architectures, with controlled ablations confirming the distinct contribution of each component.
GLaQ, a grounded latent-query framework that replaces sequential latent rollout with a fixed set of context-conditioned queries grounded in the original visual tokens, is introduced, suggesting that direct query-to-image grounding can recover localized evidence from the full image without external visual operations or...
Ze-Sheng Yang, Lingling Zhang, Xinyu Zhang et al.· 1 citation
LIRSeg is proposed, which fully replaces explicit CoT with a compact set of learnable latent tokens for reasoning segmentation, and introduces three complementary mechanisms from an information perspective: extreme-advantage sampling for selecting informative training signals, decoupled exploration-stability updates fo...
Tian-Hang Guo, Yu-Lin He, Wei Chen et al.· 0 citations
DLMR is a parameter-efficient mechanism that equips MLLMs with Dual Latent Memories: a visual memory that compresses image evidence and a reasoning memory that tracks intermediate conclusions and constraints with only a small number of additional trainable parameters.
Hao-Xuan Ma, Jin-Fei Qi, Yi-Cheng Xiao et al.· 0 citations
Recent work in visual question answering has shown that vision-language models can exhibit strong reasoning capabilities by translating visual inputs into textual representations. The effectiveness of this translation depends on how well visual details are retained; models need to surface and align both explicit and im...
Ting-Chih Chen, Emile van Krieken, Shu-Jian Yu et al.· 0 citations
UnicDocVLM is proposed, an end-to-end framework that unifies OCR and visual RAG within a single vision-language model: the model first generates a structured parse of retrieved pages, then activates question-relevant evidence from the parse to support grounded reasoning and answering.
Zong-Sheng Cao, Anran Liu, Jun Xie et al.· Proceedings of the 32nd ACM...· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduOct 15, 2026
A new computational approach reveals how cells communicate to assemble into tissues. This could accelerate stem cell engineering, improve disease models, and inform therapies.
Microsoft Research Blog· microsoft.comOct 15, 2026
Zero-knowledge proofs can verify computing results without rerunning workloads or exposing sensitive data. Magnetar helps bring them into the mainstream with support for standard programming languages, major speed gains, and quantum-resistant security. The post Proof-based general-purpose computing with Magnetar appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduSep 24, 2026
