Related papers: HyperCool: Reducing Encoding Cost in Overfitted Co…

The Internet of Things (IoT) has facilitated many applications utilizing edge-based machine learning (ML) methods to analyze locally collected data. Unfortunately, popular ML algorithms often require intensive computations beyond the…

Under certain circumstances, advanced neural video codecs can surpass the most complex traditional codecs in their rate-distortion (RD) performance. One of the main reasons for the high performance of existing neural video codecs is the use…

The promising improvement in compression efficiency of Versatile Video Coding (VVC) compared to High Efficiency Video Coding (HEVC) comes at the cost of a non-negligible encoder side complexity. The largely increased complexity overhead is…

One of the major differentiators unlocked by learned codecs relative to their hard-coded traditional counterparts is their ability to be optimized directly to appeal to the human visual system. Despite this potential, a perceptual yet…

In this paper we define the overflow problem of a network coding storage system in which the encoding parameter and the storage parameter are mismatched. Through analyses and experiments, we first show the impacts of the overflow problem in…

Entropy coding is widely used in typical learned image compression (LIC) that converts latents into a compact bitstream. However, entropy coding is typically sequential and becomes the coding latency bottleneck. To overcome it, we present…

This paper focuses on the ultimate limit theory of image compression. It proves that for an image source, there exists a coding method with shapes that can achieve the entropy rate under a certain condition where the shape-pixel ratio in…

Network coding is known to improve the throughput and the resilience to losses in most network scenarios. In a practical network scenario, however, the accurate modeling of the traffic is often too complex and/or infeasible. The goal is…

On-device continual learning (CL) is critical for edge AI systems operating on non-stationary data streams, but most existing methods rely on backpropagation or exemplar-heavy classifiers, incurring substantial compute, memory, and latency…

Hyperdimensional Computing (HDC) is emerging as a promising approach for edge AI, offering a balance between accuracy and efficiency. However, current HDC-based applications often rely on high-precision models and/or encoding matrices to…

Self-supervised vision-language models trained with contrastive objectives form the basis of current state-of-the-art methods in AI vision tasks. The success of these models is a direct consequence of the huge web-scale datasets used to…

Spiking Neural Networks (SNNs) offer significant potential for enabling energy-efficient intelligence at the edge. However, performing full SNN inference at the edge can be challenging due to the latency and energy constraints arising from…

Visual representation models leveraging attention mechanisms are challenged by significant computational overhead, particularly when pursuing large receptive fields. In this study, we aim to mitigate this challenge by introducing the Heat…

The ever-growing size of neural networks poses serious challenges on resource-constrained devices, such as embedded sensors. Compression algorithms that reduce their size can mitigate these problems, provided that model performance stays…

Recent advances in learning-based image compression typically come at the cost of high complexity. Designing computationally efficient architectures remains an open challenge. In this paper, we empirically investigate the impact of…

Lossy image and video compression algorithms yield visually annoying artifacts including blocking, blurring, and ringing, especially at low bit-rates. To reduce these artifacts, post-processing techniques have been extensively studied.…

Contrastive image-text models such as CLIP form the building blocks of many state-of-the-art systems. While they excel at recognizing common generic concepts, they still struggle on fine-grained entities which are rare, or even absent from…

Chain-of-Thought (CoT) reasoning successfully enhances the reasoning capabilities of Large Language Models (LLMs), yet it incurs substantial computational overhead for inference. Existing CoT compression methods often suffer from a critical…

The escalating adoption of high-resolution, large-field-of-view imagery amplifies the need for efficient compression methodologies. Conventional techniques frequently fail to preserve critical image details, while data-driven approaches…

Quantum error correction (QEC) is essential for quantum computing to mitigate the effect of errors on qubits, and surface code (SC) is one of the most promising QEC methods. Decoding SCs is the most computational expensive task in the…