Related papers: Multi-View Zero-Shot Open Intent Induction from Di…

Recently unpaired multi-domain image-to-image translation has attracted great interests and obtained remarkable progress, where a label vector is utilized to indicate multi-domain information. In this paper, we propose SAT (Show, Attend and…

Text-to-image models have shown remarkable progress in generating high-quality images from user-provided prompts. Despite this, the quality of these images varies due to the models' sensitivity to human language nuances. With advancements…

Although Large Language Models (LLMs) can generate coherent text, they often struggle to recognise user intent behind queries. In contrast, Natural Language Understanding (NLU) models interpret the purpose and key information of user input…

As labeling cost for different modules in task-oriented dialog (ToD) systems is high, a major challenge in practice is to learn different tasks with the least amount of labeled data. Recently, prompting methods over pre-trained language…

With the availability of massive general-domain dialogue data, pre-trained dialogue generation appears to be super appealing to transfer knowledge from the general domain to downstream applications. In most existing work, such transferable…

Audio Visual Scene-aware Dialog (AVSD) is the task of generating a response for a question with a given scene, video, audio, and the history of previous turns in the dialog. Existing systems for this task employ the transformers or…

Continual learning in task-oriented dialogue systems can allow us to add new domains and functionalities through time without incurring the high cost of a whole system retraining. In this paper, we propose a continual learning benchmark for…

Text-to-speech (TTS) systems that scale up the amount of training data have achieved significant improvements in zero-shot speech synthesis. However, these systems have certain limitations: they require a large amount of training data,…

Large-scale pre-trained language models have shown impressive results on language understanding benchmarks like GLUE and SuperGLUE, improving considerably over other pre-training methods like distributed representations (GloVe) and purely…

Generating complex multi-turn goal-oriented dialogue agents is a difficult problem that has seen a considerable focus from many leaders in the tech industry, including IBM, Google, Amazon, and Microsoft. This is in large part due to the…

There are three modalities in the reading comprehension setting: question, answer and context. The task of question answering or question generation aims to infer an answer or a question when given the counterpart based on context. We…

Large Vision Language Models have demonstrated impressive versatile capabilities through extensive multimodal pre-training, but face significant limitations when incorporating specialized knowledge domains beyond their training…

Token communications (TokCom) is an emerging generative semantic communication concept that reduces transmission rates by using context and multimodal large language model (MLLM)-based token processing, with tokens serving as universal…

Despite the surging demands for multilingual task-oriented dialog systems (e.g., Alexa, Google Home), there has been less research done in multilingual or cross-lingual scenarios. Hence, we propose a zero-shot adaptation of task-oriented…

3D Referring Expression Segmentation (3D-RES) aims to segment point cloud scenes based on a given expression. However, existing 3D-RES approaches face two major challenges: feature ambiguity and intent ambiguity. Feature ambiguity arises…

Most existing 3D referring expression segmentation (3DRES) methods rely on dense, high-quality point clouds, while real-world agents such as robots and mobile phones operate with only a few sparse RGB views and strict latency constraints.…

Currently, dialogue systems have achieved high performance in processing text-based communication. However, they have not yet effectively incorporated visual information, which poses a significant challenge. Furthermore, existing models…

User queries for a real-world dialog system may sometimes fall outside the scope of the system's capabilities, but appropriate system responses will enable smooth processing throughout the human-computer interaction. This paper is concerned…

Multimodal Large Language Models (MLLMs) have achieved great success in Speech-to-Text Translation (S2TT) tasks. However, current research is constrained by two key challenges: language coverage and efficiency. Most of the popular S2TT…

Attention-based encoder-decoder neural network models have recently shown promising results in goal-oriented dialogue systems. However, these models struggle to reason over and incorporate state-full knowledge while preserving their…