Related papers: An In-Memory Architecture for High-Performance Lon…

Developing efficient and accurate visuomotor policies poses a central challenge in robotic imitation learning. While recent rectified flow approaches have advanced visuomotor policy learning, they suffer from a key limitation: After…

In sequence to sequence learning, the self-attention mechanism proves to be highly effective, and achieves significant improvements in many tasks. However, the self-attention mechanism is not without its own flaws. Although self-attention…

Recent DNA pre-alignment filter designs employ DRAM for storing the reference genome and its associated meta-data. However, DRAM incurs increasingly high energy consumption background and refresh energy as devices scale. To overcome this…

Matched filters are widely used to localise signal patterns due to their high efficiency and interpretability. However, their effectiveness deteriorates for low signal-to-noise ratio (SNR) signals, such as those recorded on edge devices,…

We present a parallel algorithm and scalable implementation for genome analysis, specifically the problem of finding overlaps and alignments for data from "third generation" long read sequencers. While long sequences of DNA offer enormous…

For single-cell or metagenomic sequencing projects, it is necessary to sequence with a very high mean coverage in order to make sure that all parts of the sample DNA get covered by the reads produced. This leads to huge datasets with lots…

Sequential computation via autoregressive generation can make difficult tasks learnable, but the generation order of intermediate states strongly affects whether training succeeds. We address the problem of discovering a learning-friendly…

Background: Identifying all possible mapping locations of next-generation sequencing (NGS) reads is highly essential in several applications such as prediction of genomic variants or protein binding motifs located in repeat regions, isoform…

In the era of high throughput DNA sequencing (HTS) technologies, calculating the edit distance (i.e., the minimum number of substitutions, insertions, and deletions between a pair of sequences) for billions of genomic sequences is the…

Naive backpropagation through time has a memory footprint that grows linearly in the sequence length, due to the need to store each state of the forward propagation. This is a problem for large networks. Strategies have been developed to…

The so-called Forward-Forward Algorithm (FFA) has recently gained momentum as an alternative to the conventional back-propagation algorithm for neural network learning, yielding competitive performance across various modeling tasks. By…

The prefill stage of large language model (LLM) inference is a key computational bottleneck for long-context workloads. At short-to-moderate context lengths (1K--16K tokens), Feed-Forward Networks (FFNs) dominate this cost, accounting for…

DNA sequence alignment is an important workload in computational genomics. Reference-guided DNA assembly involves aligning many read sequences against candidate locations in a long reference genome. To reduce the computational load of this…

Motivation: With the development of third-generation sequencing technologies, people are able to obtain DNA sequences with lengths from 10s to 100s of kb. These long reads allow protein domain annotation without assembly, thus can produce…

Genome sequence analysis, which examines the DNA sequences of organisms, drives advances in many critical medical and biotechnological fields. Given its importance and the exponentially growing volumes of genomic sequence data, there are…

We introduce FFN Fusion, an architectural optimization technique that reduces sequential computation in large language models by identifying and exploiting natural opportunities for parallelization. Our key insight is that sequences of…

The Outstanding performance and growing size of Large Language Models has led to increased attention in parameter efficient learning. The two predominant approaches are Adapters and Pruning. Adapters are to freeze the model and give it a…

The performance of the code a compiler generates depends on the order in which it applies the optimization passes. Choosing a good order--often referred to as the phase-ordering problem, is an NP-hard problem. As a result, existing…

Genome sequences contain hundreds of millions of DNA base pairs. Finding the degree of similarity between two genomes requires executing a compute-intensive dynamic programming algorithm, such as Smith-Waterman. Traditional von Neumann…

While deep learning has achieved phenomenal successes in many AI applications, its enormous model size and intensive computation requirements pose a formidable challenge to the deployment in resource-limited nodes. There has recently been…