相关论文: Contribution-aware Token Compression for Efficient…

Convolutional Neural Networks (CNNs) have dominated computer vision for years, due to its ability in capturing locality and translation invariance. Recently, many vision transformer architectures have been proposed and they show promising…

Video compression is indispensable to most video analysis systems. Despite saving transportation bandwidth, it also deteriorates downstream video understanding tasks, especially at low-bitrate settings. To systematically investigate this…

Existing Multimodal Large Language Models (MLLMs) suffer from increased inference costs due to the additional vision tokens introduced by image inputs. In this work, we propose Visual Consistency Learning (ViCO), a novel training algorithm…

Compressed deep learning models are crucial for deploying computer vision systems on resource-constrained devices. However, model compression may affect robustness, especially under natural corruption. Therefore, it is important to consider…

Modern reasoning models, such as OpenAI's o1 and DeepSeek-R1, exhibit impressive problem-solving capabilities but suffer from critical inefficiencies: high inference latency, excessive computational resource consumption, and a tendency…

Distinct from attention-based compression methods, this paper presents an information uniqueness driven video compression framework, termed UniComp, which aims to maximize the information fidelity of video representations under constrained…

In the coded caching, the server uses the cached information at the users to serve multiple users in parallel with a single coded multi-casting message or packet, that is, a merged packet, and thus mitigates the peak network congestion. In…

In recent years, learned image compression methods have demonstrated superior rate-distortion performance compared to traditional image compression methods. Recent methods utilize convolutional neural networks (CNN), variational…

In the context of long-term video understanding with large multimodal models, many frameworks have been proposed. Although transformer-based visual compressors and memory-augmented approaches are often used to process long videos, they…

Despite advanced token compression techniques, existing multimodal large language models (MLLMs) still struggle with hour-long video understanding. In this work, we propose Video-XL-Pro, an efficient method for extremely long video…

Vision-language models (VLMs) have achieved impressive performance on multimodal reasoning tasks such as visual question answering, image captioning and so on, but their inference cost remains a significant challenge due to the large number…

This paper tackles the memory hurdle of processing long context sequences in Large Language Models (LLMs), by presenting a novel approach, Dropping In Convolutions for Long Context Compression (LoCoCo). LoCoCo employs only a fixed-size…

Efficient inference in Large Vision-Language Models is constrained by the high cost of processing thousands of visual tokens, yet it remains unclear which tokens and computations can be safely removed. While attention scores are commonly…

Online processing of compressed videos to increase their resolutions attracts increasing and broad attention. Video Super-Resolution (VSR) using recurrent neural network architecture is a promising solution due to its efficient modeling of…

Nowadays, real-time video communication over the internet through video conferencing applications has become an invaluable tool in everyone's professional and personal life. This trend underlines the need for video coding algorithms that…

Recent advancements in large video-language models have revolutionized video understanding tasks. However, their efficiency is significantly constrained by processing high volumes of visual tokens. Existing token compression strategies…

While Transformers have rapidly gained popularity in various computer vision applications, post-hoc explanations of their internal mechanisms remain largely unexplored. Vision Transformers extract visual information by representing image…

Large language models (LLMs) have demonstrated exceptional capabilities in generating text, images, and video content. However, as context length grows, the computational cost of attention increases quadratically with the number of tokens,…

Tokenized visual representations have shown promise in image compression, yet their extension to video remains underexplored due to the challenges posed by complex temporal dynamics and stringent bit rate constraints. In this paper, we…

In the era of big data, the sheer volume and complexity of datasets pose significant challenges in machine learning, particularly in image processing tasks. This paper introduces an innovative Autoencoder-based Dataset Condensation Model…