Related papers: Thinking with Video: Video Generation as a Promisi…
Reasoning-augmented machine learning systems have shown improved performance in various domains, including image generation. However, existing reasoning-based methods for image generation either restrict reasoning to a single modality…
We propose MIRA, a new benchmark designed to evaluate models in scenarios where generating intermediate visual images is essential for successful reasoning. Unlike traditional CoT methods that rely solely on text, tasks in MIRA require…
Existing Video Large Language Models (Video LLMs) struggle with complex video understanding, exhibiting limited reasoning capabilities and potential hallucinations. In particular, these methods tend to perform reasoning solely relying on…
Chain-of-Thought reasoning has driven large language models to extend from thinking with text to thinking with images and videos. However, different modalities still have clear limitations: static images struggle to represent temporal…
Recent advancements in reinforcement learning, particularly through Group Relative Policy Optimization (GRPO), have significantly improved multimodal large language models for complex reasoning tasks. However, two critical limitations…
In this paper, we introduce Motion-Grounded Video Reasoning, a new motion understanding task that requires generating visual answers (video segmentation masks) according to the input question, and hence needs implicit spatiotemporal…
Multimodal Large Language Models (MLLMs) have significantly improved performance across various image-language applications. Recently, there has been a growing interest in adapting image pre-trained MLLMs for video-related tasks. However,…
Cross-view spatial reasoning remains a weak spot for vision-language models (VLMs): they often reason in language and lose the fine-grained geometry needed for the task. Thinking with images aims to address this by generating an…
Reasoning has emerged as a pivotal capability in Large Language Models (LLMs). Through Reinforcement Learning (RL), typically Group Relative Policy Optimization (GRPO), these models are able to solve complex tasks such as mathematics and…
Despite the rapid progress of multimodal large language models (MLLMs), they have largely overlooked the importance of visual processing. In a simple yet revealing experiment, we interestingly find that language-only models, when provided…
Many video reasoning tasks require tracking motion, temporal order, and evolving visual states across frames. Existing methods built on large vision-language models (LVLMs) often address this challenge by externalizing reasoning through…
Multi-modal Large language models (MLLMs) show remarkable ability in video understanding. Nevertheless, understanding long videos remains challenging as the models can only process a finite number of frames in a single inference,…
Complex video reasoning remains a significant challenge for Multimodal Large Language Models (MLLMs), as current R1-based methodologies often prioritize text-centric reasoning derived from text-based and image-based developments. In video…
Images usually convey richer detail than text, but often include redundant information, which potentially downgrades multimodal reasoning performance. When faced with lengthy or complex messages, humans tend to employ abstract thinking to…
Multimodal Large Language Models (MLLMs) have achieved remarkable progress in vision-language tasks yet remain limited in long video understanding due to the limited context window. Consequently, prevailing approaches tend to rely on…
Despite exciting recent results showing vision-language systems' capacity to reason about images using natural language, their capacity for video reasoning remains under-explored. We motivate framing video reasoning as the sequential…
The sequential structure of videos poses a challenge to the ability of multimodal large language models (MLLMs) to locate multi-frame evidence and conduct multimodal reasoning. However, existing video benchmarks mainly focus on…
"Thinking with images" has emerged as an effective paradigm for advancing visual reasoning, extending beyond text-only chains of thought by injecting visual evidence into intermediate reasoning steps. However, existing methods fall short of…
Multimodal large language models (MLLMs) have shown strong performance on offline video understanding, but most are limited to offline inference or have weak online reasoning, making multi-turn interaction over continuously arriving video…
Recent advances in video generation have enabled the synthesis of videos with strong temporal consistency and impressive visual quality, marking a crucial step toward vision foundation models. To evaluate these video generation models,…