Related papers: InterSketch: An Interleaved Reasoning Model with S…

Reasoning is a fundamental capability for solving complex multi-step problems, particularly in visual contexts where sequential step-wise understanding is essential. Existing approaches lack a comprehensive framework for evaluating visual…

Large language models (LLMs) have shown impressive capabilities in handling complex tasks through long-chain reasoning. However, the extensive reasoning steps involved can significantly increase computational costs, posing challenges for…

Recent "Thinking with Video" approaches use Video Generation Models (VGMs) for visual reasoning by producing temporally coherent Chain-of-Frames as reasoning artifacts. Even strong VGMs, however, exhibit two recurring failure modes on…

Multimodal Large Language Models (MLLMs) have achieved remarkable performance by integrating powerful language backbones with large-scale visual encoders. Among these, latent Chain-of-Thought (CoT) methods enable implicit reasoning in…

Vision-to-code tasks require models to reconstruct structured visual inputs, such as charts, tables, and SVGs, into executable or structured representations with high visual fidelity. While recent Large Vision Language Models (LVLMs)…

Many recent prompting strategies for large language models (LLMs) query the model multiple times sequentially -- first to produce intermediate results and then the final answer. However, using these methods, both decoder and model are…

We introduce OpenVLThinker, one of the first open-source large vision-language models (LVLMs) to exhibit sophisticated chain-of-thought reasoning, achieving notable performance gains on challenging visual reasoning tasks. While text-based…

Large vision-language models (VLMs) fine-tuned on specialized visual instruction-following data have exhibited impressive language reasoning capabilities across various scenarios. However, this fine-tuning paradigm may not be able to…

Large Vision-Language Models (LVLMs) have exhibited strong reasoning capabilities through chain-of-thought mechanisms that generate step-by-step rationales. However, such slow-thinking approaches often lead to overthinking, where models…

Large Vision Language Models (LVLMs) exhibit strong Chain-of-Thought (CoT) capabilities, yet most existing paradigms assume full-video availability before inference, a batch-style process misaligned with real-world video streams where…

Multimodal Large Language Models (MLLMs) achieve strong multimodal reasoning performance, yet we identify a recurring failure mode in long-form generation: as outputs grow longer, models progressively drift away from image evidence and fall…

Process-supervised reward models serve as a fine-grained function that provides detailed step-wise feedback to model responses, facilitating effective selection of reasoning trajectories for complex tasks. Despite its advantages, evaluation…

Recent advances in visual generation have increasingly explored the integration of reasoning capabilities. They incorporate textual reasoning, i.e., think, either before (as pre-planning) or after (as post-refinement) the generation…

Despite significant progress, multimodal large language models continue to struggle with visual mathematical problem solving. Some recent works recognize that visual perception is a bottleneck in visual mathematical reasoning, but their…

Large language models (LLMs) can achieve highly effective performance on various reasoning tasks by incorporating step-by-step chain-of-thought (CoT) prompting as demonstrations. However, the reasoning chains of demonstrations generated by…

Vision language models (VLMs) are increasingly capable of reasoning over images, but robust visual reasoning often requires re-grounding intermediate steps in the underlying visual evidence. Recent approaches typically rely on external…

Spatial reasoning from monocular images is essential for autonomous driving, yet current Vision-Language Models (VLMs) still struggle with fine-grained geometric perception, particularly under large scale variation and ambiguous object…

In Large Visual Language Models (LVLMs), the efficacy of In-Context Learning (ICL) remains limited by challenges in cross-modal interactions and representation disparities. To overcome these challenges, we introduce a novel Visual…

Multimodal Large Language Models (MLLMs) have achieved significant advances in integrating visual and linguistic information, yet their ability to reason about complex and real-world scenarios remains limited. The existing benchmarks are…

Recent large vision-language models (LVLMs) can generate vision-text multimodal chain-of-thought (MCoT) traces after reinforcement fine-tuning (RFT). However, we observe that the visual information incorporated in MCoT is often inaccurate,…