Related papers: OpenMic: A Multi-Agent-Based Stand-Up Comedy Gener…
Responsing with image has been recognized as an important capability for an intelligent conversational agent. Yet existing works only focus on exploring the multimodal dialogue models which depend on retrieval-based methods, but neglecting…
Existing approaches for digital short-drama production typically rely on one-shot LLM generated scripts and loosely coupled pipelines, which fail to satisfy three key requirements of short-drama generation: (1) narrative pacing, resulting…
Effective human-AI coordination requires artificial agents capable of exhibiting and responding to human-like behaviors while adapting to changing contexts. Imitation learning has emerged as one of the prominent approaches to build such…
The proliferation of generative AI has transformed creative workflows, yet current systems face critical challenges in controllability and content protection. We propose a novel multi-agent framework that addresses both limitations through…
With the rapid progress of large language models (LLMs), LLM-powered multi-agent systems (MAS) are drawing increasing interest across academia and industry. However, many current MAS frameworks struggle with reliability and scalability,…
Humor generation remains challenging task for Large Language Models (LLMs), due to their subjective nature. We focus on satire, a form of humor strongly shaped by context. In this work, we present a novel pipeline for grounded satire…
Optimizing communication topology in LLM-based multi-agent system is critical for enabling collective intelligence. Existing methods mainly rely on spatio-temporal interaction paradigms, where the sequential execution of multi-round…
While various multimodal multi-image evaluation datasets have been emerged, but these datasets are primarily based on English, and there has yet to be a Chinese multi-image dataset. To fill this gap, we introduce RealBench, the first…
Building dialogue systems requires a large corpus of annotated dialogues. Such datasets are usually created via crowdsourcing, which is expensive and time-consuming. In this paper, we propose \textsc{Dialogic}, a novel dialogue simulation…
Integrating multiple (sub-)systems is essential to create advanced Information Systems (ISs). Difficulties mainly arise when integrating dynamic environments across the IS lifecycle. A traditional approach is a registry that provides the…
Synthesizing multi-character interactions is a challenging task due to the complex and varied interactions between the characters. In particular, precise spatiotemporal alignment between characters is required in generating close…
Generative models have recently exhibited exceptional capabilities in text-to-image generation, but still struggle to generate image sequences coherently. In this work, we focus on a novel, yet challenging task of generating a coherent…
The rapid evolution of Retrieval-Augmented Generation (RAG) toward multimodal, high-stakes enterprise applications has outpaced the development of domain specific evaluation benchmarks. Existing datasets often rely on general-domain corpora…
This paper presents OxfordTVG-HIC (Humorous Image Captions), a large-scale dataset for humour generation and understanding. Humour is an abstract, subjective, and context-dependent cognitive construct involving several cognitive factors,…
This paper presents an end-to-end pipeline for generating character-specific, emotion-aware speech from comics. The proposed system takes full comic volumes as input and produces speech aligned with each character's dialogue and emotional…
System messages play a crucial role in interactions with large language models (LLMs), often serving as prompts to initiate conversations. Through system messages, users can assign specific roles, perform intended tasks, incorporate…
Mixed-initiative dialogue tasks involve repeated exchanges of information and conversational control. Conversational agents gain control by generating responses that follow particular dialogue intents or strategies, prescribed by a policy…
Agentic task-solving with Large Language Models (LLMs) requires multi-turn, multi-step interactions, often involving complex function calls and dynamic user-agent exchanges. Existing simulation-based data generation methods for such…
Recently, interactive digital human video generation has attracted widespread attention and achieved remarkable progress. However, building such a practical system that can interact with diverse input signals in real time remains…
A previous paper presented Witscript, a system for generating conversational jokes that rely on wordplay. This paper extends that work by presenting Witscript 2, which uses a large language model to generate conversational jokes that rely…