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.
arXiv:2606. 16122v1 Announce Type: new Abstract: Visual thinking should not only sound right; it should show its evidence.
arXiv:2610.19443v1 Announce Type: new Abstract: Native multimodal pre-training trains a single model from scratch on text and multimodal data, enabling it to understand both language and visual input...
arXiv:2609.38177v1 Announce Type: cross Abstract: Reasoning about the 3D world from multi-view images remains a fundamental challenge for Multimodal Large Language Models (MLLMs). While modern MLLMs...
arXiv:2606. 03988v1 Announce Type: new Abstract: Vision language models (VLMs) excel at many tasks but still struggle with spatial reasoning when critical information is not directly observable.
arXiv:2510.23482v2 Announce Type: replace Abstract: Recent large vision-language models (LVLMs) can generate vision-text multimodal chain-of-thought (MCoT) traces after reinforcement fine-tuning (RFT...
arXiv:2610.02117v1 Announce Type: cross Abstract: On-policy self-distillation has recently emerged as an effective approach for improving language-model reasoning by supervising students with a froze...
ClueTracer is a training‑free, parameter‑free plugin that suppresses hallucinations in multimodal reasoning models by tracing how visual clues propagate from the question through the model’s reasoning pathway. It localizes task‑relevant image patches while ignoring irrelevant regions, thereby addressing the problem of reasoning drift where models over‑focus on question‑irrelevant entities. The method improves performance across various reasoning architectures by an average of 1.21× on reasoning benchmarks.
arXiv:2511. 19418v3 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) excel at reasoning in linguistic space but struggle with perceptual understanding that requires dense visual perception, e.
arXiv:2512.14691v3 Announce Type: replace Abstract: Modern multimodal generative models can synthesize visually compelling images and videos, but it remains unclear whether this visual fluency reflec...
arXiv:2610.27341v1 Announce Type: new Abstract: Vision-language models (VLMs) have advanced rapidly in multimodal reasoning, yet they remain limited on tasks requiring fine-grained understanding of s...
The paper introduces ImagiRep, a benchmark that tests spatial reasoning using seven question types across two settings, offering RGB and six alternative representations of imagined states. It shows that accurate RGB generation does not guarantee correct spatial reasoning and that different questions benefit from different representations such as depth, panoramic views, or top‑down geometry. Building on these insights, the authors present GEARS, a lightweight strategy that adaptively selects representations at test time, outperforming existing methods and demonstrating that reasoning about unseen states requires more than just RGB generation.