相关论文: BOLT: Boost Large Vision-Language Model Without Tr…

Large language models (LLMs) have demonstrated their ability to learn in-context, allowing them to perform various tasks based on a few input-output examples. However, the effectiveness of in-context learning is heavily reliant on the…

We propose an efficient evaluation protocol for large vision-language models (VLMs). Given their broad knowledge and reasoning capabilities, multiple benchmarks are needed for comprehensive assessment, making evaluation computationally…

A well-known dilemma in large vision-language models (e.g., GPT-4, LLaVA) is that while increasing the number of vision tokens generally enhances visual understanding, it also significantly raises memory and computational costs, especially…

Large language models (LLMs) have demonstrated that large-scale pretraining enables systems to adapt rapidly to new problems with little supervision in the language domain. This success, however, has not translated as effectively to the…

Multimodal large language models (MLLMs) have enabled open-world visual understanding by injecting visual input as extra tokens into large language models (LLMs) as contexts. However, when the visual input changes from a single image to a…

Large Language Models (LLMs) have demonstrated impressive performance on a wide range of natural language processing (NLP) tasks, primarily through in-context learning (ICL). In ICL, the LLM is provided with examples that represent a given…

Large Language Model (LLM) pre-training exhausts an ever growing compute budget, yet recent research has demonstrated that careful document selection enables comparable model quality with only a fraction of the FLOPs. Inspired by efforts…

Image-based visual-language (I-VL) pre-training has shown great success for learning joint visual-textual representations from large-scale web data, revealing remarkable ability for zero-shot generalisation. This paper presents a simple but…

Cross-modal video retrieval aims to retrieve the semantically relevant videos given a text as a query, and is one of the fundamental tasks in Multimedia. Most of top-performing methods primarily leverage Visual Transformer (ViT) to extract…

Large language models (LLMs) have recently been adapted to tabular prediction by serializing structured features into natural language, but their performance in low-data regimes remains limited compared to gradient-boosted decision trees…

Vision-Language Models (VLMs) have demonstrated strong capabilities in multimodal understanding and generation tasks. However, their application to long video understanding remains hindered by the quadratic complexity of standard attention…

The rapid development of Large Language Models (LLMs) has catalyzed significant advancements in video understanding technologies. This survey provides a comprehensive analysis of benchmarks and evaluation methodologies specifically designed…

To address computational and memory limitations of Large Multimodal Models in the Video Question-Answering task, several recent methods extract textual representations per frame (e.g., by captioning) and feed them to a Large Language Model…

Existing MLLMs encounter significant challenges in modeling the temporal context within long videos. Currently, mainstream Agent-based methods use external tools to assist a single MLLM in answering long video questions. Despite such…

Vision-language models (VLMs) excel in zero-shot recognition but their performance varies greatly across different visual concepts. For example, although CLIP achieves impressive accuracy on ImageNet (60-80%), its performance drops below…

Current multimodal large language models (MLLMs) struggle with hour-level video understanding, facing significant challenges not only in modeling the substantial information volume of long videos but also in overcoming the memory wall and…

Large Language Models (LLMs) have demonstrated exceptional abilities across a broad range of language-related tasks, including generating solutions to complex reasoning problems. An effective technique to enhance LLM performance is…

Large Transformer models are capable of implementing a plethora of so-called in-context learning algorithms. These include gradient descent, classification, sequence completion, transformation, and improvement. In this work, we investigate…

Adapting Multimodal Large Language Models (MLLMs) for hour-long videos is bottlenecked by context limits. Dense visual streams saturate token budgets and exacerbate the lost-in-the-middle phenomenon. Existing heuristics, like sparse…

The application of Large Multimodal Models (LMMs) to long-form video understanding is constrained by limited context lengths and the computationally prohibitive cost of processing dense video tokens. Consequently, recent research has…