Related papers: Parse indexing for discarding short pseudo-MEMs sa…

We present a merge-free algorithm for multi-way co-ranking, the problem of computing cut indices $i_1,\dots,i_m$ that partition each of the $m$ sorted sequences such that all prefix segments together contain exactly $K$ elements. Our method…

The minimizer of a word of size $k$ (a $k$-mer) is defined as its smallest substring of size $m$ (with $m\leq k$), according to some ordering on $m$-mers. minimizers have been used in bioinformatics -- notably -- to partition sequencing…

Recent research developing neural network architectures with external memory have often used the benchmark bAbI question and answering dataset which provides a challenging number of tasks requiring reasoning. Here we employed a classic…

The Segment Anything Model (SAM) achieves strong open-vocabulary segmentation, but its ViT-based image encoders dominate inference latency and memory. Existing activation compression methods, such as token merging, reduce the token length…

We present a method for identifying groups of test examples -- slices -- on which a model under-performs, a task now known as slice discovery. We formalize coherence -- a requirement that erroneous predictions, within a slice, should be…

Summary: We present a new method to incrementally construct the FM-index for both short and long sequence reads, up to the size of a genome. It is the first algorithm that can build the index while implicitly sorting the sequences in the…

Large language models (LLMs) face significant inference latency due to inefficiencies in GEMM operations, weight access, and KV cache access, especially in real-time scenarios. This highlights the need for a versatile compute-memory…

Many tasks in natural language processing, such as named entity recognition and slot-filling, involve identifying and labeling specific spans of text. In order to leverage common models, these tasks are often recast as sequence labeling…

Neural information retrieval architectures based on transformers such as BERT are able to significantly improve system effectiveness over traditional sparse models such as BM25. Though highly effective, these neural approaches are very…

Existing semi-supervised medical segmentation co-learning frameworks have realized that model performance can be diminished by the biases in model recognition caused by low-quality pseudo-labels. Due to the averaging nature of their…

Lifelong learning requires models that can continuously learn from sequential streams of data without suffering catastrophic forgetting due to shifts in data distributions. Deep learning models have thrived in the non-sequential learning…

Semantic parsers convert natural language to logical forms, which can be evaluated on knowledge bases (KBs) to produce denotations. Recent semantic parsers have been developed with sequence-to-sequence (seq2seq) pre-trained language models…

Minimum Bayes risk (MBR) decoding outputs the hypothesis with the highest expected utility over the model distribution for some utility function. It has been shown to improve accuracy over beam search in conditional language generation…

The Binary Jumbled String Matching problem is defined as: Given a string $s$ over $\{a,b\}$ of length $n$ and a query $(x,y)$, with $x,y$ non-negative integers, decide whether $s$ has a substring $t$ with exactly $x$ $a$'s and $y$ $b$'s.…

Dialect Identification (DI) is a task to recognize different dialects within the same language from a speech signal. DI can help to improve the downstream speech related tasks even when speakers have a strong dialect. However, fine-tuning a…

Recent advances in machine translation (MT) have shown that Minimum Bayes Risk (MBR) decoding can be a powerful alternative to beam search decoding, especially when combined with neural-based utility functions. However, the performance of…

In this paper, a new and novel data structure is proposed to dynamically insert and delete segments. Unlike the standard segment trees[3], the proposed data structure permits insertion of a segment with interval range beyond the interval…

We study the problem of reducing the amount of labeled training data required to train supervised classification models. We approach it by leveraging Active Learning, through sequential selection of examples which benefit the model most.…

Extreme Classification (XC) seeks to tag data points with the most relevant subset of labels from an extremely large label set. Performing deep XC with dense, learnt representations for data points and labels has attracted much attention…

The abstract of a scientific paper distills the contents of the paper into a short paragraph. In the biomedical literature, it is customary to structure an abstract into discourse categories like BACKGROUND, OBJECTIVE, METHOD, RESULT, and…