paper-with-me

Papers

Data-Centric Improvements for Enhancing Multi-Modal Understanding in Spoken Conversation Modeling

2024-12-20 · Maximillian Chen, Ruoxi Sun, Sercan Ö. Arik

Conversational assistants are increasingly popular across diverse real-world applications, highlighting the need for advanced multimodal speech modeling. Speech, as a natural mode of communication, encodes rich user-specific characteristics such as speaking rate and pitch, making it critical for effective interaction. Our work introduces a data-centric customization approach for efficiently enhancing multimodal understanding in conversational speech modeling. Central to our contributions is a novel multi-task learning paradigm that involves designing auxiliary tasks to utilize a small amount of speech data. Our approach achieves state-of-the-art performance on the Spoken-SQuAD benchmark, using only 10% of the training data with open-weight models, establishing a robust and efficient framework for audio-centric conversational modeling. We also introduce ASK-QA, the first dataset for multi-turn spoken dialogue with ambiguous user requests and dynamic evaluation inputs. Code and data forthcoming.

📄 PDF Abstract BibTeX arXiv:2412.15995

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Task Learning

Similar Papers 제목 키워드 기반

HERM: Benchmarking and Enhancing Multimodal LLMs for Human-Centric Understanding

2024-10-09 · Keliang Li, Zaifei Yang, Jiahe Zhao, Hongze Shen 외

The significant advancements in visual understanding and instruction following from Multimodal Large Language Models (MLLMs) have opened up more possibilities for broader applications in diverse and universal human-centr…

BenchmarkingInstruction Following

Visual Jigsaw Post-Training Improves MLLMs

2025-09-29 · Penghao Wu, Yushan Zhang, Haiwen Diao, Bo Li 외 arxiv

Reinforcement learning based post-training has recently emerged as a powerful paradigm for enhancing the alignment and reasoning capabilities of multimodal large language models (MLLMs). While vision-centric post-trainin…

Reinforcement Learning

LLaVA-Pose: Enhancing Human Pose and Action Understanding via Keypoint-Integrated Instruction Tuning

2025-06-26 · Dewen Zhang, Tahir Hussain, Wangpeng An, Hayaru Shouno

Current vision-language models (VLMs) are well-adapted for general visual understanding tasks. However, they perform inadequately when handling complex visual tasks related to human poses and actions due to the lack of s…

Action UnderstandingInstruction Following

Closed-Loop Transfer for Weakly-supervised Affordance Grounding

2025-10-20 · Jiajin Tang, Zhengxuan Wei, Ge Zheng, Sibei Yang arxiv

Humans can perform previously unexperienced interactions with novel objects simply by observing others engage with them. Weakly-supervised affordance grounding mimics this process by learning to locate object regions tha…

Knowledge Distillation

Keypoints-Integrated Instruction-Following Data Generation for Enhanced Human Pose Understanding in Multimodal Models

2024-09-14 · Dewen Zhang, Wangpeng An, Hayaru Shouno

Current multimodal models are well-suited for general visual understanding tasks. However, they perform inadequately when handling complex visual tasks related to human poses and actions, primarily due to the lack of spe…

Instruction Following