Related papers: STREAM: A Data-Centric Framework for Mining High-V…

Data stream mining, also known as stream learning, is a growing area which deals with learning from high-speed arriving data. Its relevance has surged recently due to its wide range of applicability, such as, critical infrastructure…

The proliferation of textual data on the Internet presents a unique opportunity for institutions and companies to monitor public opinion about their services and products. Given the rapid generation of such data, the text stream mining…

Modern visual agents require representations that are general, causal, and physically structured to operate in real-time streaming environments. However, current vision foundation models remain fragmented, specializing narrowly in image…

There has been growing interest in using neural networks and deep learning techniques to create dialogue systems. Conversational recommendation is an interesting setting for the scientific exploration of dialogue with natural language as…

Training statistical dialog models in spoken dialog systems (SDS) requires large amounts of annotated data. The lack of scalable methods for data mining and annotation poses a significant hurdle for state-of-the-art statistical dialog…

This paper introduces HyperSumm-RL, a hypertext-aware summarization and interaction analysis framework designed to investigate human perceptions of social robot leadership through long-form dialogue. The system utilizes a structured Natural…

Achieving human-like responsiveness is a critical yet challenging goal for cascaded spoken dialogue systems. Conventional ASR-LLM-TTS pipelines follow a strictly sequential paradigm, requiring complete transcription and full reasoning…

Context retrieval systems for LLM inference face a critical challenge: high retrieval latency creates a fundamental tension between waiting for complete context (poor time-to-first-token) and proceeding without it (reduced quality).…

Image generative models have made significant progress in generating realistic and diverse images, supported by comprehensive guidance from various evaluation metrics. However, current video generative models struggle to generate even short…

The majority of current Text-to-Speech (TTS) datasets, which are collections of individual utterances, contain few conversational aspects. In this paper, we introduce DailyTalk, a high-quality conversational speech dataset designed for…

Large Language Models (LLMs) excel at generating contextually appropriate responses but remain poorly calibrated for multi-party conversations, where deciding when to speak is as critical as what to say. In such settings, naively responding…

Despite advancements in conversational AI, language models encounter challenges to handle diverse conversational tasks, and existing dialogue dataset collections often lack diversity and comprehensiveness. To tackle these issues, we…

We propose a new benchmark, ComperDial, which facilitates the training and evaluation of evaluation metrics for open-domain dialogue systems. ComperDial consists of human-scored responses for 10,395 dialogue turns in 1,485 conversations…

Conversational search is a relatively young area of research that aims at automating an information-seeking dialogue. In this paper we help to position it with respect to other research areas within conversational Artificial Intelligence…

Recent progress in video large language models (Video-LLMs) has enabled strong offline reasoning over long and complex videos. However, real-world deployments increasingly require streaming perception and proactive interaction, where video…

This paper proposes a novel task on commonsense-enhanced task-based dialogue grounded in documents and describes the Task2Dial dataset, a novel dataset of document-grounded task-based dialogues, where an Information Giver (IG) provides…

Recent Speech Large Language Models~(LLMs) have achieved impressive capabilities in end-to-end speech interaction. However, the prevailing autoregressive paradigm imposes strict serial constraints, limiting generation efficiency and…

Recently, there has been an increasing interest in unifying streaming and non-streaming speech recognition models to reduce development, training and deployment cost. The best-known approaches rely on either window-based or dynamic…

Large Language Models (LLMs) have significantly improved personalized conversational capabilities. However, existing datasets like Persona Chat, Synthetic Persona Chat, and Blended Skill Talk rely on static, predefined personas. This…

In a typical customer service chat scenario, customers contact a support center to ask for help or raise complaints, and human agents try to solve the issues. In most cases, at the end of the conversation, agents are asked to write a short…