相关论文: MINERVA: Evaluating Complex Video Reasoning

The rapid advancement of native multi-modal models and omni-models, exemplified by GPT-4o, Gemini, and o3, with their capability to process and generate content across modalities such as text and images, marks a significant milestone in the…

The rapid development of multimodal large-language models (MLLMs) has significantly expanded the scope of visual language reasoning, enabling unified systems to interpret and describe complex visual content. However, applying these models…

AI models have achieved state-of-the-art results in textual reasoning; however, their ability to reason over spatial and relational structures remains a critical bottleneck -- particularly in early-grade maths, which relies heavily on…

We propose LogicVista, an evaluation benchmark that assesses the integrated logical reasoning capabilities of multimodal large language models (MLLMs) in Visual contexts. Recent advancements in MLLMs have demonstrated various fascinating…

Multimodal Large Language Models (MLLMs) struggle with complex video QA benchmarks like HD-EPIC VQA due to ambiguous queries/options, poor long-range temporal reasoning, and non-standardized outputs. We propose a framework integrating…

Vision-Language Models (VLMs) have demonstrated remarkable capabilities in interpreting visual layouts and text. However, a significant challenge remains in their ability to interpret robustly and reason over multi-tabular data presented as…

Visual reasoning is a core component of human intelligence and a critical capability for advanced multimodal models. Yet current reasoning evaluations of multimodal large language models (MLLMs) often rely on text descriptions and allow…

Recent Multimodal Large Language Models (MLLMs) achieve promising performance on visual and audio benchmarks independently. However, the ability of these models to process cross-modal information synchronously remains largely unexplored. We…

Multimodal large language models (MLLMs) excel at general video understanding but struggle with fast, high-frequency sports like tennis, where rally clips are short yet information-dense. To systematically evaluate MLLMs in this challenging…

Vision-Language Models (VLMs) have achieved strong results in video understanding, yet a key question remains: do they truly comprehend visual content or only learn shallow correlations between vision and language? Real visual…

Reinforcement fine-tuning (RFT) has shown great promise in achieving humanlevel reasoning capabilities of Large Language Models (LLMs), and has recently been extended to MLLMs. Nevertheless, reasoning about videos, which is a fundamental…

Recent advancements in multimodal reward models (RMs) have substantially improved post-training for visual generative models. However, current RMs face inherent limitations: (1) visual inputs consume large context budgets, forcing fewer…

Recent advances in Multimodal Large Language Models (MLLMs) have significantly improved performance on tasks such as visual grounding and visual question answering. However, the reasoning processes of these models remain largely opaque;…

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…

We introduce a full-stack framework that scales up reasoning in vision-language models (VLMs) to long videos, leveraging reinforcement learning. We address the unique challenges of long video reasoning by integrating three critical…

Deeply understanding sports requires an intricate blend of fine-grained visual perception and rule-based reasoning - a challenge that pushes the limits of current multimodal models. To succeed, models must master three critical…

In the field of multimodal chain-of-thought (CoT) reasoning, existing approaches predominantly rely on reasoning on pure language space, which inherently suffers from language bias and is largely confined to math or science domains. This…

Multimodal Large Language Models (MLLMs) have achieved significant advancements in tasks like Visual Question Answering (VQA) by leveraging foundational Large Language Models (LLMs). However, their abilities in specific areas such as visual…

Recent studies have demonstrated the effectiveness of Large Language Models (LLMs) as reasoning modules that can deconstruct complex tasks into more manageable sub-tasks, particularly when applied to visual reasoning tasks for images. In…

Integrating external tools into Large Foundation Models (LFMs) has emerged as a promising approach to enhance their problem-solving capabilities. While existing studies have demonstrated strong performance in tool-augmented Visual Question…