Related papers: TargetCall: Eliminating the Wasted Computation in …
The emergence of reasoning-based LLMs leveraging Chain-of-Thought (CoT) inference introduces new serving challenges, as their extended reasoning phases delay user-visible output and inflate Time-To-First-Token (TTFT). Existing LLM serving…
Restricting the system calls available to applications reduces the attack surface of the kernel and limits the functionality available to compromised applications. Recent approaches automatically identify the system calls required by…
The 2020 Personalized Voice Trigger Challenge (PVTC2020) addresses two different research problems a unified setup: joint wake-up word detection with speaker verification on close-talking single microphone data and far-field multi-channel…
DNA sequencing is the physical/biochemical process of identifying the location of the four bases (Adenine, Guanine, Cytosine, Thymine) in a DNA strand. As semiconductor technology revolutionized computing, modern DNA sequencing technology…
A long-standing vision of backscatter communications is to provide long-range connectivity and high-speed transmissions for batteryless Internet-of-Things (IoT). Recent years have seen major innovations in designing backscatters toward this…
RNA plays a pivotal role in translating genetic instructions into functional outcomes, underscoring its importance in biological processes and disease mechanisms. Despite the emergence of numerous deep learning approaches for RNA,…
We introduce BERTphone, a Transformer encoder trained on large speech corpora that outputs phonetically-aware contextual representation vectors that can be used for both speaker and language recognition. This is accomplished by training on…
Nanopore sequencers generate electrical raw signals in real-time while sequencing long genomic strands. These raw signals can be analyzed as they are generated, providing an opportunity for real-time genome analysis. An important feature of…
The analyst effort in data cleaning is gradually shifting away from the design of hand-written scripts to building and tuning complex pipelines of automated data cleaning libraries. Hyper-parameter tuning for data cleaning is very different…
Target speech separation refers to isolating target speech from a multi-speaker mixture signal by conditioning on auxiliary information about the target speaker. Different from the mainstream audio-visual approaches which usually require…
Fine-tuning provides an effective means to specialize pre-trained models for various downstream tasks. However, fine-tuning often incurs high memory overhead, especially for large transformer-based models, such as LLMs. While existing…
Rapid development of large-scale pre-training has resulted in foundation models that can act as effective feature extractors on a variety of downstream tasks and domains. Motivated by this, we study the efficacy of pre-trained vision models…
Transcriptions of phone calls are of significant value across diverse fields, such as sales, customer service, healthcare, and law enforcement. Nevertheless, the analysis of these recorded conversations can be an arduous and time-intensive…
Code large language models mark a pivotal breakthrough in artificial intelligence. They are specifically crafted to understand and generate programming languages, significantly boosting the efficiency of coding development workflows. In…
In this paper, a novel architecture for speaker recognition is proposed by cascading speech enhancement and speaker processing. Its aim is to improve speaker recognition performance when speech signals are corrupted by noise. Instead of…
Analyses of targeted genomic sequencing data from next-generation-sequencing (NGS) technologies typically involves mapping reads to a reference sequence or clustering reads. For a number of species a reference genome is not available so the…
Current AI-powered code assistance tools often struggle with poorly-defined problem statements that lack sufficient task context and requirements specification. Recent analysis of software engineering agents reveals that failures on such…
The presence of noisy instances in mobile phone data is a fundamental issue for classifying user phone call behavior (i.e., accept, reject, missed and outgoing), with many potential negative consequences. The classification accuracy may…
Researchers have investigated the potential of leveraging pre-trained language models, such as CodeBERT, to enhance source code-related tasks. Previous methodologies have relied on CodeBERT's '[CLS]' token as the embedding representation of…
With the rapid growth of Web-based academic publications, more and more papers are being published annually, making it increasingly difficult to find relevant prior work. Citation prediction aims to automatically suggest appropriate…