Related papers: QSVD: Efficient Low-rank Approximation for Unified…

Vision-language models (VLMs) have demonstrated strong capabilities in multimodal perception and reasoning. However, deploying large VLMs on mobile devices remains challenging due to their substantial computational and memory demands. A…

Vision-Language Large Models (VLLMs) face significant efficiency challenges when processing high-resolution inputs. The quadratic complexity in attention and autoregressive generation, as well as the constantly growing key value (KV) cache…

In this paper we propose novel methods for compression and recovery of multilinear data under limited sampling. We exploit the recently proposed tensor- Singular Value Decomposition (t-SVD)[1], which is a group theoretic framework for…

Document parsing is a fine-grained task where image resolution significantly impacts performance. While advanced research leveraging vision-language models benefits from high-resolution input to boost model performance, this often leads to…

Vision Language Models (VLMs) offer the exciting possibility of processing text as rendered images, bypassing the need for tokenizing the text into long token sequences. Since VLM image encoders map fixed-size images to a fixed number of…

Large language models (LLMs) are omnipresent, however their practical deployment is challenging due to their ever increasing computational and memory demands. Quantization is one of the most effective ways to make them more compute and…

The emergence of LLMs has ignited a fresh surge of breakthroughs in NLP applications, particularly in domains such as question-answering systems and text generation. As the need for longer context grows, a significant bottleneck in model…

Recent advancements in Vision-Language Models (VLMs) have enabled complex multimodal tasks by processing text and image data simultaneously, significantly enhancing the field of artificial intelligence. However, these models often exhibit…

Large Language models (LLMs) have become a research hotspot. To accelerate the inference of LLMs, storing computed caches in memory has become the standard technique. However, as the inference length increases, growing KV caches might lead…

Large Language Models (LLMs) excel in natural language processing tasks but pose significant computational and memory challenges for edge deployment due to their intensive resource demands. This work addresses the efficiency of LLM…

Multimodal large language models (MLLMs) are plagued by exorbitant inference costs attributable to the profusion of visual tokens within the vision encoder. The redundant visual tokens engenders a substantial computational load and…

The randomized singular value decomposition (RSVD) is by now a well established technique for efficiently computing an approximate singular value decomposition of a matrix. Building on the ideas that underpin the RSVD, the recently proposed…

Large Vision-Language Models (VLMs) have achieved remarkable success in multi-modal reasoning, but their inference time efficiency remains a significant challenge due to the memory overhead during decoding, especially when the query and…

Generative Large Multimodal Models (LMMs) like LLaVA and Qwen-VL excel at a wide variety of vision-language (VL) tasks. Despite strong performance, LMMs' generative outputs are not specialized for vision-language classification tasks (i.e.,…

Large language models (LLMs) are widely deployed with rapidly expanding context windows to support increasingly demanding applications. However, long contexts pose significant deployment challenges, primarily due to the KV cache whose size…

The growing computational and memory demands of the Key-Value (KV) cache significantly limit the ability of Large Language Models (LLMs). While KV merging has emerged as a promising solution, existing methods that rely on empirical…

Recently, significant progress has been made in developing reasoning-capable Large Language Models (LLMs) through long Chain-of-Thought (CoT) techniques. However, this long-CoT reasoning process imposes substantial memory overhead due to…

KV caching is a fundamental technique for accelerating Large Language Model (LLM) inference by reusing key-value (KV) pairs from previous queries, but its effectiveness under limited memory is highly sensitive to the eviction policy. The…

Existing approaches for improving the efficiency of Large Vision-Language Models (LVLMs) are largely based on the concept of visual token reduction. This approach, however, creates an information bottleneck that impairs performance,…

Model quantization has become a crucial technique to address the issues of large memory consumption and long inference times associated with LLMs. Mixed-precision quantization, which distinguishes between important and unimportant…