Related papers: Focus: A Streaming Concentration Architecture for …

Recent advancements in vision-language models (VLMs) have improved performance by increasing the number of visual tokens, which are often significantly longer than text tokens. However, we observe that most real-world scenarios do not…

Modern multimodal large language models (MLLMs) adopt a unified self-attention design that processes visual and textual tokens at every Transformer layer, incurring substantial computational overhead. In this work, we revisit the necessity…

Multimodal large language models (MLLMs) have achieved impressive performance, but high-resolution visual inputs result in long sequences of visual tokens and substantial inference latency. Reducing redundant visual tokens is critical to…

Long-context reasoning has significantly empowered large language models (LLMs) to tackle complex tasks, yet it introduces severe efficiency bottlenecks due to the computational complexity. Existing efficient approaches often rely on…

Multi-modal Large Langue Models (MLLMs) often process thousands of visual tokens, which consume a significant portion of the context window and impose a substantial computational burden. Prior work has empirically explored visual token…

Recent advances in Multimodal Large Language Models (MLLMs) have expanded reasoning capabilities into 3D domains, enabling fine-grained spatial understanding. However, the substantial size of 3D MLLMs and the high dimensionality of input…

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…

With the rapid development of large multimodal models (LMMs), multimodal understanding applications are emerging. As most LMM inference requests originate from edge devices with limited computational capabilities, the predominant inference…

Generative conversational interfaces powered by large language models (LLMs) typically stream output token-by-token at a rate determined by computational budget, often neglecting actual human reading speeds and the cognitive load associated…

Scaling the input image resolution is essential for enhancing the performance of Vision Language Models (VLMs), particularly in text-rich image understanding tasks. However, popular visual encoders such as ViTs become inefficient at high…

Vision-Language Models (vLLMs) have emerged as powerful architectures for joint reasoning over visual and textual inputs, enabling breakthroughs in image captioning, cross modal retrieval, and multimodal dialogue. However, as these models…

Vision-Language Models (VLMs) have advanced rapidly within the unified Transformer architecture, yet their deployment on resource-constrained devices remains challenging due to high computational complexity. While pruning has emerged as an…

Recently, large-scale pre-training methods like CLIP have made great progress in multi-modal research such as text-video retrieval. In CLIP, transformers are vital for modeling complex multi-modal relations. However, in the vision…

By treating visual tokens from visual encoders as text tokens, Multimodal Large Language Models (MLLMs) have achieved remarkable progress across diverse visual understanding tasks, leveraging the robust architectures of Large Language…

Large language models (LLMs) have enabled the creation of multi-modal LLMs that exhibit strong comprehension of visual data such as images and videos. However, these models usually rely on extensive visual tokens from visual encoders,…

Vision-language models (VLMs) face significant computational inefficiencies caused by excessive generation of visual tokens. While prior work shows that a large fraction of visual tokens are redundant, existing compression methods struggle…

This paper presents VideoStreaming, an advanced vision-language large model (VLLM) for video understanding, that capably understands arbitrary-length video with a constant number of video tokens streamingly encoded and adaptively selected.…

Video-language models (VLMs) face rapid inference costs as visual token counts scale with video length. For example, 32 frames at $448{\times}448$ resolution already yield >8,000 visual tokens in Qwen3-VL, making LLM prefill the dominant…

Most multimodal large language models (MLLMs) treat visual tokens as "a sequence of text", integrating them with text tokens into a large language model (LLM). However, a great quantity of visual tokens significantly increases the demand…

Large vision-language models (VLMs) have demonstrated remarkable capabilities in open-world multimodal understanding, yet their high computational overheads pose great challenges for practical deployment. Some recent works have proposed…