相关论文: Efficient Dynamic WFST Decoding for Personalized L…

Neural text-to-speech (TTS) models can synthesize natural human speech when trained on large amounts of transcribed speech. However, collecting such large-scale transcribed data is expensive. This paper proposes an unsupervised pre-training…

Large language models (LLMs) have revolutionized natural language processing and broadened their applicability across diverse commercial applications. However, the deployment of these models is constrained by high inference time in…

Large language models (LLMs) are increasingly employed for complex tasks that process multiple generation calls in a tree structure with shared prefixes of tokens, including few-shot prompting, multi-step reasoning, speculative decoding,…

Communication complexity and privacy are the two key challenges in Federated Learning where the goal is to perform a distributed learning through a large volume of devices. In this work, we introduce FedSKETCH and FedSKETCHGATE algorithms…

With the growing use of large language models (LLMs) hosted on cloud platforms to offer inference services, privacy concerns about the potential leakage of sensitive information are escalating. Secure multi-party computation (MPC) is a…

Masked Diffusion Models (MDMs) offer a promising alternative to autoregressive language models by enabling parallel token generation and bidirectional context modeling. However, their inference speed is significantly limited by the…

Realizing personalized intelligence faces a core dilemma: sending user history to centralized large language models raises privacy concerns, while on-device small language models lack the reasoning capacity required for high-quality…

Forecasting over graph-structured sensor networks demands models that capture both deterministic spatial trends and stochastic variability, while remaining efficient enough for repeated inference as new observations arrive. We propose…

In recent years, deep learning-based approaches have significantly improved the performance of single-channel speech enhancement. However, due to the limitation of training data and computational complexity, real-time enhancement of…

In this paper, we describe the work that we have done to participate in Task1 of the ConferencingSpeech2021 challenge. This task set a goal to develop the solution for multi-channel speech enhancement in a real-time manner. We propose a…

We present a novel inference scheme, self-speculative decoding, for accelerating Large Language Models (LLMs) without the need for an auxiliary model. This approach is characterized by a two-stage process: drafting and verification. The…

Decentralized Federated Learning (DFL) has emerged as a robust distributed paradigm that circumvents the single-point-of-failure and communication bottleneck risks of centralized architectures. However, a significant challenge arises as…

Decentralized learning with private data is a central problem in machine learning. We propose a novel distillation-based decentralized learning technique that allows multiple agents with private non-iid data to learn from each other,…

Recent advances in linguistic steganalysis have successively applied CNN, RNN, GNN and other efficient deep models for detecting secret information in generative texts. These methods tend to seek stronger feature extractors to achieve…

Recent advances in conditional recurrent language modelling have mainly focused on network architectures (e.g., attention mechanism), learning algorithms (e.g., scheduled sampling and sequence-level training) and novel applications (e.g.,…

Diffusion Large Language Models (dLLMs) enable breakthroughs in reasoning and parallel decoding but suffer from prohibitive quadratic computational complexity and memory overhead during inference. Current caching techniques accelerate…

Scaling language models to longer contexts is essential for capturing rich dependencies across extended discourse. However, na\"ive context extension imposes significant computational and memory burdens, often resulting in inefficiencies…

Personalizing automatic speech recognition (ASR) systems for non-normative speech, such as dysarthric and aphasic speech, is challenging. While speaker-specific fine-tuning (SS-FT) is widely used, it is typically initialized directly from a…

Test-time scaling (TTS), which involves dynamic allocation of compute during inference, offers a promising way to improve reasoning in large language models. While existing TTS methods work well, they often rely on long decoding paths or…

Systems that can associate images with their spoken audio captions are an important step towards visually grounded language learning. We describe a scalable method to automatically generate diverse audio for image captioning datasets. This…