Related papers: PARCEL: Pool-Anchored Resampling with Conditioned …

Vision-language models (VLMs) have transformed multimodal reasoning, but feeding hundreds of visual patch tokens into LLMs incurs quadratic computational costs, straining memory and context windows. Traditional approaches face a trade-off:…

Vision-language models (VLMs) excel at image understanding tasks, but the large number of visual tokens imposes significant computational costs, hindering deployment on mobile devices. Many pruning methods rely solely on token importance…

Multimodal Large Language Models (MLLMs) encounter significant computational and memory bottlenecks from the massive number of visual tokens generated by high-resolution images or multi-image inputs. Previous token compression techniques…

Multimodal large language models (MLLMs) have achieved strong performance on vision-language tasks, yet often suffer from inefficiencies due to redundant visual tokens. Existing token merging methods reduce sequence length but frequently…

Human perception of visual similarity is inherently adaptive and subjective, depending on the users' interests and focus. However, most image retrieval systems fail to reflect this flexibility, relying on a fixed, monolithic metric that…

Lookup tables are a fundamental structure in many data processing and systems applications. Examples include tokenized text in NLP, quantized embedding collections in recommendation systems, integer sketches for streaming data, and…

The visual projector serves as an essential bridge between the visual encoder and the Large Language Model (LLM) in a Multimodal LLM (MLLM). Typically, MLLMs adopt a simple MLP to preserve all visual contexts via one-to-one transformation.…

Self-attention mechanisms model long-range context by using pairwise attention between all input tokens. In doing so, they assume a fixed attention granularity defined by the individual tokens (e.g., text characters or image pixels), which…

Large Vision-Language Models (LVLMs) process multimodal inputs consisting of text tokens and vision tokens extracted from images or videos. Due to the rich visual information, a single image can generate thousands of vision tokens, leading…

Vision-Language-Action (VLA) models have emerged as a powerful paradigm in Embodied AI. However, the significant computational overhead of processing redundant visual tokens remains a critical bottleneck for real-time robotic deployment.…

Vision Language Models (VLMs) have rapidly advanced in integrating visual and textual reasoning, powering applications across high-resolution image understanding, long-video analysis, and multi-turn conversation. However, their scalability…

Recent advances on Multi-modal Large Language Models have demonstrated that high-resolution image input is crucial for model capabilities, especially for fine-grained tasks. However, high-resolution images lead to a quadratic increase in…

Existing visual token compression methods for Multimodal Large Language Models (MLLMs) predominantly operate as post-encoder modules, limiting their potential for efficiency gains. To address this limitation, we propose LaCo (Layer-wise…

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…

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…

Large Vision-Language Models (LVLMs) have recently demonstrated strong multimodal understanding, yet their fine-grained visual perception is often constrained by low input resolutions. A common remedy is to partition high-resolution images…

Document layout analysis aims to detect and categorize structural elements (e.g., titles, tables, figures) in scanned or digital documents. Popular methods often rely on high-quality Optical Character Recognition (OCR) to merge visual…

Self-supervised vision-language pretraining from pure images and text with a contrastive loss is effective, but ignores fine-grained alignment due to a dual-stream architecture that aligns image and text representations only on a global…

The application of Large Vision-Language Models (LVLMs) for analyzing images and videos is an exciting and rapidly evolving field. In recent years, we've seen significant growth in high-quality image-text datasets for fine-tuning image…

Audio-Visual Large Language Models (AV-LLMs) face prohibitive computational overhead from massive audio and video tokens. Token reduction, while extensively explored for video-only LLMs, is insufficient for the audio-visual domain, as these…