相关论文: Semantic and Visual Evidence for Efficient Long-Vi…

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…

Large Multimodal Models (LMMs) have achieved remarkable progress across various capabilities; however, complex video reasoning in the scientific domain remains a significant and challenging frontier. Current video benchmarks predominantly…

Large vision-language models (LVLMs) have demonstrated remarkable achievements, yet the generation of non-factual responses remains prevalent in fact-seeking question answering (QA). Current multimodal fact-seeking benchmarks primarily…

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…

Multimodal large language models (MLLMs) are increasingly considered as a foundation for embodied agents, yet it remains unclear whether they can reliably reason about the long-term physical consequences of actions from an egocentric…

Large Vision-Language Models (LVLMs) offer remarkable benefits for a variety of vision-language tasks. However, a challenge hindering their application in real-world scenarios, particularly regarding safety, robustness, and reliability, is…

Long-form video understanding with Large Vision Language Models is challenged by the need to analyze temporally dispersed yet spatially concentrated key moments within limited context windows. In this work, we introduce VideoMindPalace, a…

Large Vision-Language Models (LVLMs) have shown remarkable progress in various multimodal tasks, yet they often struggle with complex visual reasoning that requires multi-step inference. To address this limitation, we propose MF-SQ-LLaVA, a…

While vision-language models (VLMs) excel at tasks involving single images or short videos, they still struggle with Long Video Question Answering (LVQA) due to its demand for complex multi-step temporal reasoning. Vanilla approaches, which…

Multimodal Large Language Models (MLLMs) have shown strong performance in visual and audio understanding when evaluated in isolation. However, their ability to jointly reason over omni-modal (visual, audio, and textual) signals in long and…

Video Question Answering (VQA) requires models to reason over spatial, temporal, and causal cues in videos. Recent vision language models (VLMs) achieve strong results but often rely on shallow correlations, leading to weak temporal…

Video spatial reasoning requires accumulating viewpoint-dependent evidence over time while retaining information useful to the question being asked. Existing spatial video-language models improve geometric perception and long-range context…

Despite remarkable recent progress, existing long-form VideoQA datasets fall short of meeting the criteria for genuine long-form video understanding. This is primarily due to the use of short videos for question curation, and the reliance…

Multimodal emotion analysis is shifting from static classification to generative reasoning. Beyond simple label prediction, robust affective reasoning must synthesize fine-grained signals such as facial micro-expressions and prosodic which…

Large Multimodal Models (LMMs), or Vision-Language Models (VLMs), have shown impressive capabilities in a wide range of visual tasks. However, they often struggle with fine-grained visual reasoning, failing to identify domain-specific…

Long-term agent memory is increasingly multimodal, yet existing evaluations rarely test whether agents preserve the visual evidence needed for later reasoning. In prior work, many visually grounded questions can be answered using only…

Training multimodal large language models (MLLMs) for video understanding requires large-scale annotated data spanning diverse tasks such as object counting, question answering, and segmentation. However, collecting and annotating…

Understanding long video content is a complex endeavor that often relies on densely sampled frame captions or end-to-end feature selectors, yet these techniques commonly overlook the logical relationships between textual queries and visual…

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…

In this work, we present a novel method to tackle the token generation challenge in Vision Language Models (VLMs) for video and image understanding, called LLaMA-VID. Current VLMs, while proficient in tasks like image captioning and visual…