相关论文: Variational Latent-State GPT for Semi-Supervised T…

Intent detection, a critical component in task-oriented dialogue (TOD) systems, faces significant challenges in adapting to the rapid influx of integrable tools with complex interrelationships. Existing approaches, such as zero-shot…

This paper investigates the challenges and potential solutions for improving machine learning systems for low-resource languages. State-of-the-art models in natural language processing (NLP), text-to-speech (TTS), speech-to-text (STT), and…

Parallel text-to-speech (TTS) models have recently enabled fast and highly-natural speech synthesis. However, they typically require external alignment models, which are not necessarily optimized for the decoder as they are not jointly…

Recently, pre-training methods have shown remarkable success in task-oriented dialog (TOD) systems. However, most existing pre-trained models for TOD focus on either dialog understanding or dialog generation, but not both. In this paper, we…

Parallel test-time scaling (TTS) is a pivotal approach for enhancing large language models (LLMs), typically by sampling multiple token-based chains-of-thought in parallel and aggregating outcomes through voting or search. Recent advances…

Medical dialogue generation aims to provide automatic and accurate responses to assist physicians to obtain diagnosis and treatment suggestions in an efficient manner. In medical dialogues two key characteristics are relevant for response…

Intelligent task-oriented dialogue systems (ToDs) are expected to continuously acquire new knowledge, also known as Continual Learning (CL), which is crucial to fit ever-changing user needs. However, catastrophic forgetting dramatically…

In real-world applications, it is often expensive and time-consuming to obtain labeled examples. In such cases, knowledge transfer from related domains, where labels are abundant, could greatly reduce the need for extensive labeling…

Vision-Language-Action (VLA) models benefit from chain-of-thought (CoT) reasoning, but existing approaches incur high inference overhead and rely on discrete reasoning representations that mismatch continuous perception and control. We…

Recent advances in speech language models (LLMs) have extended textual LLMs to the speech domain, but balancing speech understanding and generation remains challenging, especially with codec-based representations. We propose a continual…

Auto-regressive speech-text models pre-trained on interleaved text tokens and discretized speech tokens demonstrate strong speech understanding and generation, yet remain substantially less compute-efficient than text LLMs, partly due to…

This paper proposes an effective emotional text-to-speech (TTS) system with a pre-trained language model (LM)-based emotion prediction method. Unlike conventional systems that require auxiliary inputs such as manually defined emotion…

Recently, deep learning-based Text-to-Speech (TTS) systems have achieved high-quality speech synthesis results. Recurrent neural networks have become a standard modeling technique for sequential data in TTS systems and are widely used.…

We propose a Vision-Language Transformer (VLT) framework for referring segmentation to facilitate deep interactions among multi-modal information and enhance the holistic understanding to vision-language features. There are different ways…

Maintaining good driving behavior in out-of-distribution scenarios remains a critical challenge in autonomous driving. A promising direction is to leverage the generalist knowledge and reasoning capabilities of large-language models by…

Inference-time scaling (ITS) in latent reasoning models typically relies on heuristic perturbations, such as dropout or fixed Gaussian noise, to generate diverse candidate trajectories. However, we show that stronger perturbations do not…

Several fully end-to-end text-to-speech (TTS) models have been proposed that have shown better performance compared to cascade models (i.e., training acoustic and vocoder models separately). However, they often generate unstable pitch…

Pre-trained models have proved to be powerful in enhancing task-oriented dialog systems. However, current pre-training methods mainly focus on enhancing dialog understanding and generation tasks while neglecting the exploitation of dialog…

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…

Despite significant advances in Large Reasoning Models (LRMs) driven by reinforcement learning with verifiable rewards (RLVR), this paradigm is fundamentally limited in specialized or novel domains where such supervision is prohibitively…