Related papers: FreqCache: Accelerating Embodied VLN Models with A…

The success of deep neural networks (DNN) in machine perception applications such as image classification and speech recognition comes at the cost of high computation and storage complexity. Inference of uncompressed large scale DNN models…

Large models achieve strong performance on Vision-and-Language Navigation (VLN) tasks, but are costly to run in resource-limited environments. Token pruning offers appealing tradeoffs for efficiency with minimal performance loss by reducing…

Visual token compression is widely adopted to improve the inference efficiency of Large Vision-Language Models (LVLMs), enabling their deployment in latency-sensitive and resource-constrained scenarios. However, existing work has mainly…

Notwithstanding the significant research effort Network Function Virtualization (NFV) architectures received over the last few years little attention has been placed on optimizing proactive caching when considering it as a service chain.…

Harvesting dense pixel-level annotations to train deep neural networks for semantic segmentation is extremely expensive and unwieldy at scale. While learning from synthetic data where labels are readily available sounds promising,…

The emerging vision-and-language navigation (VLN) problem aims at learning to navigate an agent to the target location in unseen photo-realistic environments according to the given language instruction. The main challenges of VLN arise…

This paper presents FluxMem, a training-free framework for efficient streaming video understanding. FluxMem adaptively compresses redundant visual memory through a hierarchical, two-stage design: (1) a Temporal Adjacency Selection (TAS)…

Deploying Vision-Language Models (VLMs) on edge devices remains challenging due to their substantial computational and memory demands, which exceed the capabilities of resource-constrained embedded platforms. Conversely, fully offloading…

Current high-resolution vision-language models encode images as high-resolution image tokens and exhaustively take all these tokens to compute attention, which significantly increases the computational cost. To address this problem, we…

Deep neural networks have achieved remarkable success in computer vision tasks. Existing neural networks mainly operate in the spatial domain with fixed input sizes. For practical applications, images are usually large and have to be…

Understanding the internal process of ConvNets is commonly done using visualization techniques. However, these techniques do not usually provide a tool for estimating the stability of a ConvNet against noise. In this paper, we show how to…

Recent literature including our past work provide analysis and solutions for using (i) erasure coding, (ii) parallelism, or (iii) variable slicing/chunking (i.e., dividing an object of a specific size into a variable number of smaller…

This paper proposes VLA-AN, an efficient and onboard Vision-Language-Action (VLA) framework dedicated to autonomous drone navigation in complex environments. VLA-AN addresses four major limitations of existing large aerial navigation…

As the field of Large Language Models (LLMs) continues to evolve, the context length in inference is steadily growing. Key-Value Cache (KVCache), the intermediate representations of tokens within LLM inference, has now become the primary…

Multimodal Large Language Models (MLLMs) have recently demonstrated strong performance across a wide range of vision-language tasks, garnering significant attention in the computer vision. However, their efficient deployment remains a…

Vector databases have become a cornerstone of modern information retrieval, powering applications in recommendation, search, and retrieval-augmented generation (RAG) pipelines. However, scaling approximate nearest neighbor (ANN) search to…

Invisible watermarking is essential for safeguarding digital content, enabling copyright protection and content authentication. However, existing watermarking methods fall short in robustness against regeneration attacks. In this paper, we…

As Video Large Language Models (Video-LLMs) scale to longer and more complex videos, their inference cost grows rapidly due to the large volume of visual tokens accumulated across frames. Training-free token compression has emerged as a…

Unlike offline processing, streaming video vision-language models face two fundamental constraints: causality and accumulation. Causality prevents access to future frames that offline methods exploit, while accumulation causes tokens to…

In this work, we design and implement VQ-LLM, an efficient fused Vector Quantization (VQ) kernel generation framework. We first introduce a software abstraction called codebook cache to optimize codebook access efficiency and support the…