Related papers: Fast, Dense Feature SDM on an iPhone

With the rapid emergence of a spectrum of high-end mobile devices, many applications that required desktop-level computation capability formerly can now run on these devices without any problem. However, without a careful optimization,…

Weight pruning has been widely acknowledged as a straightforward and effective method to eliminate redundancy in Deep Neural Networks (DNN), thereby achieving acceleration on various platforms. However, most of the pruning techniques are…

While the literature has been fairly dense in the areas of scene understanding and semantic labeling there have been few works that make use of motion cues to embellish semantic performance and vice versa. In this paper, we address the…

This paper explores the feasibility and performance of on-device large language model (LLM) inference on various Apple iPhone models. Amidst the rapid evolution of generative AI, on-device LLMs offer solutions to privacy, security, and…

It is appealing but challenging to achieve real-time deep neural network (DNN) inference on mobile devices because even the powerful modern mobile devices are considered as ``resource-constrained'' when executing large-scale DNNs. It…

This paper presents a general framework to build fast and accurate algorithms for video enhancement tasks such as super-resolution, deblurring, and denoising. Essential to our framework is the realization that the accuracy, rather than the…

Image restoration aims to restore high-quality images from degraded counterparts and has seen significant advancements through deep learning techniques. The technique has been widely applied to mobile devices for tasks such as mobile…

With the prevalence of multimodal learning, camera-LiDAR fusion has gained popularity in 3D object detection. Although multiple fusion approaches have been proposed, they can be classified into either sparse-only or dense-only fashion based…

Mobile authentication using behavioral biometrics has been an active area of research. Existing research relies on building machine learning classifiers to recognize an individual's unique patterns. However, these classifiers are not…

Linear-scaling implementations of density functional theory (DFT) reach their intended efficiency regime only when applied to systems having a physical size larger than the range of their Kohn-Sham density matrix (DM). This causes a problem…

Speculative Decoding has gained popularity as an effective technique for accelerating the auto-regressive inference process of Large Language Models. However, Speculative Decoding entirely relies on the availability of efficient draft…

It is always well believed that Binary Neural Networks (BNNs) could drastically accelerate the inference efficiency by replacing the arithmetic operations in float-valued Deep Neural Networks (DNNs) with bit-wise operations. Nevertheless,…

Various deep learning applications on smartphones have been rapidly rising, but training deep neural networks (DNNs) has too large computational burden to be executed on a single smartphone. A portable cluster, which connects smartphones…

We revisit the widely used bss eval metrics for source separation with an eye out for performance. We propose a fast algorithm fixing shortcomings of publicly available implementations. First, we show that the metrics are fully specified by…

Motion blur restoration on consumer mobile devices is typically evaluated using aggregate metrics that obscure performance variation across blur difficulty, masking model behavior under real deployment conditions. This work introduces…

AI-powered automatic camera scene detection mode is nowadays available in nearly any modern smartphone, though the problem of accurate scene prediction has not yet been addressed by the research community. This paper for the first time…

We propose MFT -- Multi-Flow dense Tracker -- a novel method for dense, pixel-level, long-term tracking. The approach exploits optical flows estimated not only between consecutive frames, but also for pairs of frames at logarithmically…

Large language models (LLMs) underpin interactive multimedia applications such as captioning, retrieval, recommendation, and creative content generation, yet their autoregressive decoding incurs substantial latency. Speculative decoding…

In many applications, we collect independent samples from interconnected populations. These population distributions share some latent structure, so it is advantageous to jointly analyze the samples. One effective way to connect the…

Speculative decoding (SD) has emerged as a widely used paradigm to accelerate LLM inference without compromising quality. It works by first employing a compact model to draft multiple tokens efficiently and then using the target LLM to…