paper-with-me

Papers

S3: A Simple Strong Sample-effective Multimodal Dialog System

2024-06-26 · Elisei Rykov, Egor Malkershin, Alexander Panchenko

In this work, we present a conceptually simple yet powerful baseline for the multimodal dialog task, an S3 model, that achieves near state-of-the-art results on two compelling leaderboards: MMMU and AI Journey Contest 2023. The system is based on a pre-trained large language model, pre-trained modality encoders for image and audio, and a trainable modality projector. The proposed effective data mixture for training such an architecture demonstrates that a multimodal model based on a strong language model and trained on a small amount of multimodal data can perform efficiently in the task of multimodal dialog.

📄 PDF Abstract BibTeX arXiv:2406.18305

Code (1)

s-nlp/s3 공식 구현 pytorch

Tasks

Language ModelingLanguage ModellingLarge Language Model

Similar Papers 제목 키워드 기반

SimpleMTOD: A Simple Language Model for Multimodal Task-Oriented Dialogue with Symbolic Scene Representation

2023-07-10 · Bhathiya Hemanthage, Christian Dondrup, Phil Bartie, Oliver Lemon

SimpleMTOD is a simple language model which recasts several sub-tasks in multimodal task-oriented dialogues as sequence prediction tasks. SimpleMTOD is built on a large-scale transformer-based auto-regressive architectur…

coreference-resolutionCoreference Resolutiondialog state trackingLanguage Modeling+3

LLaVAShield: Safeguarding Multimodal Multi-Turn Dialogues in Vision-Language Models

2025-09-30 · Guolei Huang, Qinzhi Peng, Gan Xu, Yao Huang 외 arxiv

As Vision-Language Models (VLMs) move into interactive, multi-turn use, safety concerns intensify for multimodal multi-turn dialogue, which is characterized by concealment of malicious intent, contextual risk accumulatio…

Red Teaming

DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encoder

2018-05-31 · ICLR 2019 5 · Xiaodong Gu, Kyunghyun Cho, Jung-Woo Ha, Sunghun Kim

Variational autoencoders~(VAEs) have shown a promise in data-driven conversation modeling. However, most VAE conversation models match the approximate posterior distribution over the latent variables to a simple prior su…

Response Generation

'No' Matters: Out-of-Distribution Detection in Multimodality Long Dialogue

2024-10-31 · Rena Gao, Xuetong Wu, Siwen Luo, Caren Han 외

Out-of-distribution (OOD) detection in multimodal contexts is essential for identifying deviations in combined inputs from different modalities, particularly in applications like open-domain dialogue systems or real-life…

Out-of-Distribution DetectionOut of Distribution (OOD) Detection

DialogGraph-LLM: Graph-Informed LLMs for End-to-End Audio Dialogue Intent Recognition

2025-11-14 · HongYu Liu, Junxin Li, Changxi Guo, Hao Chen 외 arxiv

Recognizing speaker intent in long audio dialogues among speakers has a wide range of applications, but is a non-trivial AI task due to complex inter-dependencies in speaker utterances and scarce annotated data. To addre…

Intent Recognition