Related papers: FastOCR: Dynamic Visual Fixation via KV Cache Prun…

Optical Character Recognition (OCR) is a fundamental task for digitizing information, serving as a critical bridge between visual data and textual understanding. While modern Vision-Language Models (VLM) have achieved high accuracy in this…

Large Multimodal Models (LMMs) excel in visual-language tasks by leveraging numerous visual tokens for fine-grained visual information, but this token redundancy results in significant computational costs. Previous research aimed at…

Large Language Models (LLMs) struggle with long-context code due to window limitations. Existing textual code compression methods mitigate this via selective filtering but often disrupt dependency closure, causing semantic fragmentation. To…

Current VLM-based VQA methods often process entire images, leading to excessive visual tokens that include redundant information irrelevant to the posed question. This abundance of unnecessary image details creates numerous visual tokens,…

Vision-Language Models (VLMs) have demonstrated impressive performance across a versatile set of tasks. A key challenge in accelerating VLMs is storing and accessing the large Key-Value (KV) cache that encodes long visual contexts, such as…

Vision-language models (VLMs) typically encode substantially more visual tokens than text tokens, resulting in significant token redundancy. Pruning uninformative visual tokens is therefore crucial for improving computational efficiency,…

Vision-Language Models (VLMs) have achieved notable success in multimodal tasks but face practical limitations due to the quadratic complexity of decoder attention mechanisms and autoregressive generation. Existing methods like FASTV and…

Vision-Language-Action (VLA) models have shown great potential for embodied AI by integrating visual perception, language understanding, and action execution. In real-time deployment, these models must process continuous visual streams,…

Document parsing is a core task in document intelligence, supporting applications such as information extraction, retrieval-augmented generation, and automated document analysis. However, real-world documents often feature complex layouts…

Vision-Language Models (VLMs) have revolutionized multi-modal learning by jointly processing visual and textual information. Yet, they face significant challenges due to the high computational and memory demands of processing long sequences…

Vision-Language Models (VLMs) have recently demonstrated remarkable capabilities in visual understanding and reasoning, but they also impose significant computational burdens due to long visual sequence inputs. Recent works address this…

Multimodal Large Language Models (MLLMs) have shown strong performance in vision-language tasks, but their inference efficiency is severely limited by the exponential growth of visual tokens in complex scenarios such as high-resolution…

Visual token compression is critical for Large Vision-Language Models (LVLMs) to efficiently process high-resolution inputs. Existing methods that typically adopt fixed compression ratios cannot adapt to scenes of varying complexity, often…

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…

Billions of public domain documents remain trapped in hard copy or lack an accurate digitization. Modern natural language processing methods cannot be used to index, retrieve, and summarize their texts; conduct computational textual…

Vision-language models (VLMs) predominantly rely on autoregressive decoding, which generates tokens one at a time and fundamentally limits inference throughput. This limitation is especially acute in physical AI scenarios such as robotics…

Recent advances in vision-language models have demonstrated remarkable performance across diverse multi-modal tasks, including document question answering that leverages structured visual cues from text, tables, and figures. However, unlike…

Visual token pruning is a promising approach for reducing the computational cost of vision-language models (VLMs), and existing methods often rely on early pruning decisions to improve efficiency. While effective on coarse-grained reasoning…

Real-time inference of vision-language-action (VLA) models is essential for robotic control. While visual token pruning has shown strong potential for accelerating inference, most existing methods mainly base pruning decisions on…

While large language models (LLMs) excel at handling long-context sequences, they require substantial prefill computation and key-value (KV) cache, which can heavily burden computational efficiency and memory usage in both prefill and…