VITAL introduces a visual‑semantic dual supervision framework for latent reasoning in medical multimodal large language models. It uses an auxiliary text decoder to reconstruct reasoning chains from latent states and a visual projector to regress ROI features from a frozen medical vision encoder, both discarded during inference to avoid overhead. The approach yields a 61K dataset across nine imaging modalities and achieves state‑of‑the‑art performance on seven benchmarks, outperforming existing latent reasoning baselines and large medical MLLMs.
arXiv:2604. 09757v2 Announce Type: replace-cross Abstract: Medical vision--language models (VLMs) have shown strong potential for medical visual question answering (VQA), yet their reasoning remains largely text-centric: images are encoded once as static context, and subsequent inference is dominated by language.
arXiv:2604.07518v2 Announce Type: replace Abstract: Vision-Language Models often struggle with complex visual reasoning due to the visual information loss in textual CoT. Existing methods either add...
arXiv:2606. 12169v1 Announce Type: cross Abstract: High-stakes clinical use of large vision-language models (LVLMs) requires reasoning that is grounded in visual evidence and clinical knowledge, not just correct final answers.
arXiv:2609.34798v2 Announce Type: replace Abstract: Recent medical multimodal models have benefited from larger corpora, broader modality coverage, and stronger reasoning-oriented training, yet effec...
arXiv:2606. 00562v1 Announce Type: cross Abstract: The emerging paradigm of "thinking with images" embeds visual states into intermediate reasoning steps, defining a new frontier for Vision-Language Models.
arXiv:2603. 07131v4 Announce Type: replace-cross Abstract: Large Vision Language Models (LVLMs) show immense potential for automated ophthalmic diagnosis.
arXiv:2603. 25629v2 Announce Type: replace-cross Abstract: While language reasoning models excel in many tasks, visual reasoning remains challenging for current large multimodal models (LMMs).
arXiv:2608. 03450v1 Announce Type: cross Abstract: Reasoning in Multimodal Large Language Models (MLLMs) requires both fine-grained visual perception and rigorous logical deduction.
Recent advancements in chain-of-thought (CoT) reasoning have shown promise in enhancing video understanding and reasoning capabilities of multimodal large language models (MLLMs). However, existing CoT-based MLLMs require labor-intensive CoT annotations and incur substantial training and inference overhead.
SLVR (Structured Latent Visual Reasoning) is a training framework that blends explicit chain-of-thought with latent reasoning for multimodal large language models. It organizes reasoning into typed latent stages—planning, grounding, evidence selection, and integration—each supervised by corresponding signals such as plans, bounding boxes, visual evidence, and final rationales. Built on Qwen2.5‑VL‑7B, SLVR consistently improves performance on multimodal reasoning benchmarks, achieving significant gains on MMVP, BLINK Relation, V*, MathVista, and ChartQA.
The paper introduces LARK, a two‑stage latent reasoning framework designed to mitigate cross‑modal dilution in multimodal recommendation systems. In the first stage, learnable latent tokens are interleaved with chain‑of‑thought reasoning and aligned with a frozen vision encoder to preserve visual details. The second stage projects these latent representations through a bridge MLP, employing item‑to‑item contrastive learning and aligning intermediate features with the first‑stage hidden states to anchor final embeddings to the model’s reasoning output. Experiments on three public benchmarks and an industrial dataset demonstrate that LARK achieves state‑of‑the‑art performance across multiple recommendation architectures, with ablation studies confirming the contribution of each component.
LiteMedCoT-VL is a parameter‑efficient pipeline that transfers chain‑of‑thought reasoning from a 235B teacher model to a 2B student model using LoRA fine‑tuning on explanation‑enriched data. The approach enables a compact vision‑language model to perform medical visual question answering without relying on image captions, achieving 64.9% accuracy on the PMC‑VQA benchmark—an 11‑point improvement over the zero‑shot Qwen3‑VL‑4B baseline. Visual grounding analysis confirms that the model bases its predictions on image content rather than textual priors.