Related papers: Cascaded Mutual Modulation for Visual Reasoning
Existing multimodal reasoning approaches predominantly follow two paradigms: converting visual inputs into text prior to reasoning, or performing end-to-end reasoning within a unified vision-language representation space. Despite their…
Language models (LMs) and their extension, vision-language models (VLMs), have achieved remarkable performance across various tasks. However, they still struggle with complex reasoning tasks that require multimodal or multilingual…
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…
While Large Language Models (LLMs) excel at reasoning on text and Vision-Language Models (VLMs) are highly effective for visual perception, applying those models for visual instruction-based planning remains a widely open problem. In this…
Current large vision-language models (LVLMs) typically employ a connector module to link visual features with text embeddings of large language models (LLMs) and use end-to-end training to achieve multi-modal understanding in a unified…
Recent advances in vision-language models (VLMs) have greatly improved cross-modal semantic understanding, yet significant limitations remain in fine-grained discrimination and deep causal reasoning tasks. Existing VLMs often rely on…
Video captioning is a critical task in the field of multimodal machine learning, aiming to generate descriptive and coherent textual narratives for video content. While large vision-language models (LVLMs) have shown significant progress,…
Recent breakthroughs in computer vision and natural language processing have spurred interest in challenging multi-modal tasks such as visual question-answering and visual dialogue. For such tasks, one successful approach is to condition…
In our work, we explore the synergistic capabilities of pre-trained vision-and-language models (VLMs) and large language models (LLMs) on visual commonsense reasoning (VCR) problems. We find that VLMs and LLMs-based decision pipelines are…
We introduce a general-purpose conditioning method for neural networks called FiLM: Feature-wise Linear Modulation. FiLM layers influence neural network computation via a simple, feature-wise affine transformation based on conditioning…
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…
Visual language reasoning requires a system to extract text or numbers from information-dense images like charts or plots and perform logical or arithmetic reasoning to arrive at an answer. To tackle this task, existing work relies on…
Existing visual question answering methods often suffer from cross-modal spurious correlations and oversimplified event-level reasoning processes that fail to capture event temporality, causality, and dynamics spanning over the video. In…
Current Large Language Models (LLMs) and Vision-Language Large Models (LVLMs) excel in single-turn tasks but face significant challenges in multi-turn interactions requiring deep contextual understanding and complex visual reasoning, often…
Open-source multimodal large language models (MLLMs) excel in various tasks involving textual and visual inputs but still struggle with complex multimodal mathematical reasoning, lagging behind proprietary models like GPT-4V(ision) and…
Complex Visual Question Answering (Complex VQA) tasks, which demand sophisticated multi-modal reasoning and external knowledge integration, present significant challenges for existing large vision-language models (LVLMs) often limited by…
The rapid advancement of Large Language Models (LLMs) and Large Vision-Language Models (LVLMs) has enhanced our ability to process and generate human language and visual information. However, these models often struggle with complex,…
Fine-grained image classification, particularly in zero/few-shot scenarios, presents a significant challenge for vision-language models (VLMs), such as CLIP. These models often struggle with the nuanced task of distinguishing between…
While language reasoning models excel in many tasks, visual reasoning remains challenging for current large multimodal models (LMMs). As a result, most LMMs default to verbalizing perceptual content into text, a strong limitation for tasks…
Recent advancements in Vision-Language (VL) research have sparked new benchmarks for complex visual reasoning, challenging models' advanced reasoning ability. Traditional Vision-Language Models (VLMs) perform well in visual perception tasks…