Related papers: RUBICON: A Framework for Designing Efficient Deep …
Supervised deep learning methods require a large repository of annotated data; hence, label noise is inevitable. Training with such noisy data negatively impacts the generalization performance of deep neural networks. To combat label noise,…
The DNA sequencing is the process of identifying the exact order of nucleotides within a given DNA molecule. The new portable and relatively inexpensive DNA sequencers, such as Oxford Nanopore MinION, have the potential to move DNA…
Deep learning applications are usually very compute-intensive and require a long run time for training and inference. This has been tackled by researchers from both hardware and software sides, and in this paper, we propose a Roofline-based…
Token generation speed is critical to power the next wave of AI inference applications. GPUs significantly underperform during token generation due to synchronization overheads at kernel boundaries, utilizing only 21% of their peak memory…
Recently, deep clustering (DPCL) based speaker-independent speech separation has drawn much attention, since it needs little speaker prior information. However, it still has much room of improvement, particularly in reverberant…
Current tokenization methods process sequential data without accounting for signal quality, limiting their effectiveness on noisy real-world corpora. We present QA-Token (Quality-Aware Tokenization), which incorporates data reliability…
The rapid proliferation of Deep Learning is increasingly constrained by its heavy reliance on high-performance hardware, particularly Graphics Processing Units (GPUs). These specialized accelerators are not only prohibitively expensive and…
Recent research has shown that transformer networks can be used as differentiable search indexes by representing each document as a sequences of document ID tokens. These generative retrieval models cast the retrieval problem to a document…
Accurate RNA structure modeling remains difficult because RNA backbones are highly flexible, non-canonical interactions are prevalent, and experimentally determined 3D structures are comparatively scarce. We introduce \emph{RiboSphere}, a…
Chain-of-thought has been proven essential for enhancing the complex reasoning abilities of Large Language Models (LLMs), but it also leads to high computational costs. Recent advances have explored the method to route queries among…
DNA sequence encoding is fundamental to gene function prediction, protein synthesis, and diverse downstream biological tasks. Despite the substantial progress achieved by large-scale DNA sequence pretraining, existing studies have…
Deep Neural Networks (DNNs) are the de facto algorithm for tackling cognitive tasks in real-world applications such as speech recognition and natural language processing. DNN inference comprises numerous dot product operations between…
The ability to compositionally map language to referents, relations, and actions is an essential component of language understanding. The recent gSCAN dataset (Ruis et al. 2020, NeurIPS) is an inspiring attempt to assess the capacity of…
This paper introduces a novel multimodal and high-resolution human brain cerebellum lobule segmentation method. Unlike current tools that operate at standard resolution ($1 \text{ mm}^{3}$) or using mono-modal data, the proposed method…
Deep learning recommendation systems must provide high quality, personalized content under strict tail-latency targets and high system loads. This paper presents RecPipe, a system to jointly optimize recommendation quality and inference…
Understanding the spectrum of noise acting on a qubit can yield valuable information about its environment, and crucially underpins the optimization of dynamical decoupling protocols that can mitigate such noise. However, extracting…
Across scientific domains, a fundamental challenge is to characterize and compute the mappings from underlying physical processes to observed signals and measurements. While nonlinear neural networks have achieved considerable success, they…
It has recently been shown that radio interferometric gain calibration can be expressed succinctly in the language of complex optimisation. In addition to providing an elegant framework for further development, it exposes properties of the…
Complex problems, whether in math, logic, or planning, are solved by humans through a sequence of steps where the result of one step informs the next. In this work, we adopt the perspective that the reasoning power of Transformers is…
The task of learning from point cloud data is always challenging due to the often occurrence of noise and outliers in the data. Such data inaccuracies can significantly influence the performance of state-of-the-art deep learning networks…