Related papers: TRIO: Token Reduction via Inference-Objective Guid…

We propose Vision Token Turing Machines (ViTTM), an efficient, low-latency, memory-augmented Vision Transformer (ViT). Our approach builds on Neural Turing Machines and Token Turing Machines, which were applied to NLP and sequential visual…

DeepSeek-OCR leverages visual-text compression to reduce long-text processing costs and accelerate inference, yet visual tokens remain prone to redundant textual and structural information. Moreover, current token pruning methods for…

Integrating vision models into large language models (LLMs) has sparked significant interest in creating vision-language foundation models, especially for video understanding. Recent methods often utilize memory banks to handle untrimmed…

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 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 tokens dominate inference cost in vision-language models (VLMs), yet many carry redundant information. Existing pruning methods alleviate this but typically rely on attention magnitude or similarity scores. We reformulate visual…

Are low-attention visual tokens truly redundant in vision-language reasoning? Existing pruning methods often assume so, ranking visual tokens by shallow text-to-image attention and discarding low-scoring patches to accelerate LVLM…

Current vision-language models (VLMs) still exhibit inferior performance on knowledge-intensive tasks, primarily due to the challenge of accurately encoding all the associations between visual objects and scenes to their corresponding…

In Vision Language Models (VLMs), vision tokens are quantity-heavy yet information-dispersed compared with language tokens, thus consume too much unnecessary computation. Pruning redundant vision tokens for high VLM inference efficiency has…

Diffusion-based large multimodal models, such as LLaDA-V, have demonstrated impressive capabilities in vision-language understanding and generation. However, their bidirectional attention mechanism and diffusion-style iterative denoising…

Token compression techniques have recently emerged as powerful tools for accelerating Vision Transformer (ViT) inference in computer vision. Due to the quadratic computational complexity with respect to the token sequence length, these…

Recent achievements of vision-language models in end-to-end OCR point to a new avenue for low-loss compression of textual information. This motivates earlier works that render the Transformer's input into images for prefilling, which…

While Large Vision-Language Models (LVLMs) demonstrate exceptional multi-modal capabilities, the quadratic computational cost of processing high-resolution visual tokens remains a critical bottleneck. Though recent token reduction…

Vision-Language Models (VLMs) incur substantial computational overhead and inference latency due to the large number of vision tokens introduced by high-resolution image and video inputs. Existing parameter-free token compression methods…

We propose a collaborative edge-to-server inference framework for vision-language models (VLMs) that reduces the communication cost while maintaining inference accuracy. In typical deployments, visual data captured at edge devices (clients)…

Diffusion Large Language Models (DLLMs) promise fast parallel generation, yet open-source DLLMs still face a severe quality-speed trade-off: accelerating decoding by revealing multiple tokens often causes substantial quality degradation. We…

This paper introduces VideoScan, an efficient vision-language model (VLM) inference framework designed for real-time video interaction that effectively comprehends and retains streamed video inputs while delivering rapid and accurate…

Vision Transformers (ViTs) excel in semantic segmentation but demand significant computation, posing challenges for deployment on resource-constrained devices. Existing token pruning methods often overlook fundamental visual data…

Prevailing Multimodal Large Language Models (MLLMs) encode the input image(s) as vision tokens and feed them into the language backbone, similar to how Large Language Models (LLMs) process the text tokens. However, the number of vision…

Vision-Language Models (VLMs) enable powerful multimodal reasoning but suffer from slow autoregressive inference, limiting their deployment in real-time applications. We introduce Spec-LLaVA, a system that applies speculative decoding to…