This work proposes Latent Visual Contrastive Reasoning, a branch-aware latent reasoning framework that generates multiple question-conditioned latent visual branches as soft hypotheses over image tokens and introduces a soft contrastive branch-evidence alignment objective.
Abstract
Multimodal large language models have made substantial progress in visual question answering, but complex visual reasoning often requires locating and comparing multiple pieces of question-relevant visual evidence. Existing methods that move intermediate reasoning into the visual latent space usually follow a single linear reasoning trajectory, which can be limiting when multiple visual hypotheses or competing evidence regions are relevant. We propose Latent Visual Contrastive Reasoning, a branch-aware latent reasoning framework that generates multiple question-conditioned latent visual branches as soft hypotheses over image tokens. To train these branches, our method uses bounding-box evidence annotations to build target evidence representations and introduces a soft contrastive branch-evidence alignment objective. This objective encourages evidence-relevant branches to align with annotated visual regions while contrasting them against negative evidence. We instantiate our method on Qwen2.5-VL backbones and train it with standard supervised fine-tuning. Experiments on perception-intensive visual reasoning benchmarks show that the proposed method achieves overall improvements over the corresponding backbone and single-path latent reasoning baselines at both 3B and 7B scales.
Multimodal large language models (MLLMs) often answer visual reasoning questions by relying on linguistic priors rather than task-relevant visual evidence. Textual chain-of-thought reasoning can partially mitigate this issue by encouraging models to decompose visual questions into intermediate evidence-seeking steps, b...
Chain-of-thought reasoning has substantially advanced video understanding in multimodal large language models (MLLMs). However, language-based reasoning traces do not provide a reliable mechanism for models to revisit relevant visual evidence, leading to visual forgetting and impairing their ability to reason over vide...
Shi-Long Li, Xing-Yuan Bu, Hao Shi et al.· 0 citations
V2T first trains a teacher LVLM using interleaved visual and textual chains of thought, and then uses knowledge distillation to train a student LVLM using the teacher's logits and cross-entropy supervision from ground-truth textual reasoning.
Wen-Han Yang, Nilay Naharas, Ali Payani et al.· arXiv.org· 0 citations
ReaLVR is proposed, which brings visual-evidence supervision to the model's own free-running latent trajectories, and is the first to scale visual reasoning in latent space, showing that the framework continues to deliver robust improvements at frontier model scales up to 235B.
Xi Xiao, Tian-Chen Zhao, Youngeun Kim et al.· arXiv.org· 2 citations
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...
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.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.