The paper investigates latent visual reasoning in multimodal large language models, treating input, latent tokens, and final answer as a causal chain. Causal mediation analysis reveals two disconnections: latent tokens largely ignore input perturbations, and changes to latent tokens minimally affect the final answer, indicating limited causal influence. Probing shows latent tokens encode little visual information and are highly similar, leading the authors to propose CapImagine, an explicit text‑based imagination approach that outperforms latent‑space baselines on vision‑centric benchmarks.
arXiv:2606. 01287v1 Announce Type: cross Abstract: Recent latent visual reasoning methods achieve substantial gains by inserting continuous latent tokens into multimodal language models.
arXiv:2605.18641v2 Announce Type: replace Abstract: Latent visual reasoning involves visual evidence more directly in multimodal reasoning by inserting continuous latent tokens before textual generat...
The paper introduces Causal Visual Recurrent Reasoning (CVRR), a method that forces multimodal models to rely on latent visual states by using recurrent computation as the sole image‑conditioned path to prediction. CVRR initializes recurrence from the question hidden state after a pretrained vision‑language model has processed the image, repeatedly updates this state while re‑reading the same visual evidence, and removes all other visual traces before decoding. Experiments on several benchmarks show that CVRR maintains strong performance while other latent reasoners lose visual competence, and causal interventions confirm that predictions depend on the recurrent visual trajectory.
arXiv:2610.01917v1 Announce Type: cross Abstract: Latent visual reasoning equips vision--language models with continuous intermediate states that can process visual evidence without explicit textual...
arXiv:2608. 15869v1 Announce Type: cross Abstract: Multimodal large language models increasingly use visual chain-of-thought (Visual CoT) to reason about spatial, temporal, and embodied environments.
The paper introduces LIRSeg, a method that replaces explicit Chain-of-Thought reasoning in multimodal large language models with a compact set of learnable latent tokens for reasoning segmentation. LIRSeg is trained in two stages—spatial alignment and GRPO—while employing extreme-advantage sampling, decoupled exploration-stability updates, and latent diversity amplification to enhance token informativeness. Experiments show that LIRSeg improves segmentation accuracy and reasoning efficiency, achieving significant gIoU gains over the VisionReasoner baseline and reducing reasoning tokens by about 16×.
arXiv:2605.05593v2 Announce Type: replace Abstract: Despite the remarkable success of Multimodal Large Language Models (MLLMs) across diverse tasks, the internal mechanisms governing how they encode...
arXiv:2601. 10129v2 Announce Type: replace-cross Abstract: Current multimodal latent reasoning often relies on external supervision (e.
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: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.
The study examines how Vision‑Language Models (VLMs) integrate visual evidence into language‑based decisions by applying layer‑wise causal interventions on video‑text attention pathways in a video‑based generative multiple‑choice setting. Findings reveal that visual information is primarily incorporated while processing candidate answer options, with nouns serving as key semantic anchors and verbs becoming important during temporal reasoning. The research also uncovers a distinct pattern in temporal reasoning, indicating that VLMs struggle to reconstruct sequential information across video frames, possibly due to linguistic biases in temporal expressions.
arXiv:2609.37656v1 Announce Type: new Abstract: Large vision-language models (LVLMs) exhibit strong reasoning capabilities, yet the visual and textual evidence supporting the generated responses rema...