Related papers: An Efficient Inference Frame for SMLM (Single-Mole…

In this paper, we introduce a novel self-supervised learning (SSL) loss for image representation learning. There is a growing belief that generalization in deep neural networks is linked to their ability to discriminate object shapes. Since…

Dense pixel matching is important for many computer vision tasks such as disparity and flow estimation. We present a robust, unified descriptor network that considers a large context region with high spatial variance. Our network has a very…

The limited context window of contemporary large language models (LLMs) remains a primary bottleneck for their broader application across diverse domains. Although continual pre-training on long-context data offers a straightforward…

Compressed Sensing MRI reconstructs images of the body's internal anatomy from undersampled measurements, thereby reducing scan time. Recently, deep learning has shown great potential for reconstructing high-fidelity images from highly…

The landscape of video recognition has evolved significantly, shifting from traditional Convolutional Neural Networks (CNNs) to Transformer-based architectures for improved accuracy. While 3D CNNs have been effective at capturing…

In robotic task planning, symbolic planners using rule-based representations like PDDL are effective but struggle with long-sequential tasks in complicated environments due to exponentially increasing search space. Meanwhile, LLM-based…

Recent advancements in speculative decoding have demonstrated considerable speedup across a wide array of large language model (LLM) tasks. Speculative decoding inherently relies on sacrificing extra memory allocations to generate several…

Brain midline shift (MLS) is one of the most critical factors to be considered for clinical diagnosis and treatment decision-making for intracranial hemorrhage. Existing computational methods on MLS quantification not only require intensive…

Despite the recent visually-pleasing results achieved, the massive computational cost has been a long-standing flaw for diffusion probabilistic models (DPMs), which, in turn, greatly limits their applications on resource-limited platforms.…

This paper presents ServerlessLLM, a distributed system designed to support low-latency serverless inference for Large Language Models (LLMs). By harnessing the substantial near-GPU storage and memory capacities of inference servers,…

Deep neural networks have demonstrated highly competitive performance in super-resolution (SR) for natural images by learning mappings from low-resolution (LR) to high-resolution (HR) images. However, hyperspectral super-resolution remains…

Deploying Large Language Models (LLMs) on edge devices remains challenging due to their quadratically increasing computations with the sequence length. Existing studies for dynamic attention pruning are designed for hardware with massively…

Driven by the new generation of multi-modal large models, such as Stable Diffusion (SD), image manipulation technologies have advanced rapidly, posing significant challenges to image forensics. However, existing image forgery localization…

Large language models (LLMs) have demonstrated exceptional proficiency in understanding and generating human language, but efficient inference on resource-constrained embedded devices remains challenging due to large model sizes and…

Decentralized machine learning (DML) supports collaborative training in large-scale networks with no central server. It is sensitive to the quality and reliability of inter-device communications that result in time-varying and stochastic…

All-in-one image restoration seeks to recover clean images from inputs affected by diverse and unknown degradations using a unified framework. Recent methods have shown strong performance by identifying degradation characteristics to guide…

The evolution of Large Language Models from the Transformer architecture to models with trillions of parameters has shifted the primary bottleneck from model training to real time inference. Deploying these massive models is a complex…

Transformers have sprung up in the field of computer vision. In this work, we explore whether the core self-attention module in Transformer is the key to achieving excellent performance in image recognition. To this end, we build an…

Deep Metric Learning (DML) methods have been proven relevant for visual similarity learning. However, they sometimes lack generalization properties because they are trained often using an inappropriate sample selection strategy or due to…

State-space models (SSMs) are powerful probabilistic tools for modeling time-varying systems with latent dynamics. Inference in SSMs involves the estimation of latent states and parameters. In this work, we focus on parameter inference,…