相关论文: Super Monotonic Alignment Search

Neural embedding models are extensively employed in the table union search problem, which aims to find semantically compatible tables that can be merged with a given query table. In particular, multi-vector models, which represent a table…

Current text-to-speech (TTS) models face a persistent limitation: autoregressive (AR) models suffer from low generation efficiency, while modern non-autoregressive (NAR) models experience high latency due to their unordered temporal nature.…

TAPS is a Topology-Aware intra-operator Parallelism strategy Searching algorithm that generates intra-operator parallelism strategies by considering both intra-node and inter-node bandwidth. Most of the existing auto-parallelism works use…

Test-Time Scaling (TTS) has proven effective in improving the performance of Large Language Models (LLMs) during inference. However, existing research has overlooked the efficiency of TTS from a latency-sensitive perspective. Through a…

This work presents a lifelong learning approach to train a multilingual Text-To-Speech (TTS) system, where each language was seen as an individual task and was learned sequentially and continually. It does not require pooled data from all…

We present FMAS, a fast multi-objective neural architecture search framework for semantic segmentation. FMAS subsamples the structure and pre-trained parameters of DeepLabV3+, without fine-tuning, dramatically reducing training time during…

Nearest Neighbor Search (NNS) has recently drawn a rapid increase of interest due to its core role in managing high-dimensional vector data in data science and AI applications. The interest is fueled by the success of neural embedding,…

In the realm of Text-Based Person Search (TBPS), mainstream methods aim to explore more efficient interaction frameworks between text descriptions and visual data. However, recent approaches encounter two principal challenges. Firstly, the…

Neural Text-to-Speech (TTS) systems find broad applications in voice assistants, e-learning, and audiobook creation. The pursuit of modern models, like Diffusion Models (DMs), holds promise for achieving high-fidelity, real-time speech…

Test-Time Scaling (TTS) enhances the reasoning ability of large language models (LLMs) by allocating additional computation during inference. However, existing approaches primarily rely on output-level sampling while overlooking the role of…

Vision-language models such as CLIP have shown impressive capabilities in aligning images and text, but they often struggle with lengthy and detailed text descriptions due to pre-training on short and concise captions. We present FAST-GOAL…

We propose to incorporate neural architecture search (NAS) into general-purpose multi-task learning (GP-MTL). Existing NAS methods typically define different search spaces according to different tasks. In order to adapt to different task…

Aligning acoustic and linguistic representations is a central challenge to bridge the pre-trained models in knowledge transfer for automatic speech recognition (ASR). This alignment is inherently structured and asymmetric: while multiple…

Non-autoregressive translation (NAT) models are typically trained with the cross-entropy loss, which forces the model outputs to be aligned verbatim with the target sentence and will highly penalize small shifts in word positions. Latent…

Defining and finalizing Mergers and Acquisitions (M&A) requires complex human skills, which makes it very hard to automatically find the best partner or predict which firms will make a deal. In this work, we propose the MASS algorithm, a…

In this paper, we present a fast and strong neural approach for general purpose text matching applications. We explore what is sufficient to build a fast and well-performed text matching model and propose to keep three key features…

Current Text-to-Speech (TTS) systems typically use separate models for speech-prompted and text-prompted timbre control. While unifying both control signals into a single model is desirable, the challenge of cross-modal alignment often…

The mismatch of speech length and text length poses a challenge in automatic speech recognition (ASR). In previous research, various approaches have been employed to align text with speech, including the utilization of Connectionist…

While large language models (LLMs) have revolutionized text-to-speech (TTS) synthesis through discrete tokenization paradigms, current architectures exhibit fundamental tensions between three critical dimensions: 1) irreversible loss of…

Modern applications frequently collect and analyze temporal data in the form of multivariate time series (MTS) -- time series that contain multiple channels. A common task in this context is subsequence search, which involves identifying…