Cover Image

Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Gang, Liu, Jizhong, Dinkel, Heinrich, Niu, Yadong, Zhang, Junbo, Luan, Jian
Format:	Preprint
Published:	2025
Subjects:	Sound Artificial Intelligence Computation and Language Audio and Speech Processing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MECAT: A Multi-Experts Constructed Benchmark for Fine-Grained Audio Understanding Tasks
by: Niu, Yadong, et al.
Published: (2025)

MiDashengLM: Efficient Audio Understanding with General Audio Captions
by: Dinkel, Heinrich, et al.
Published: (2025)

GLAP: General contrastive audio-text pretraining across domains and languages
by: Dinkel, Heinrich, et al.
Published: (2025)

X-ARES: A Comprehensive Framework for Assessing Audio Encoder Performance
by: Zhang, Junbo, et al.
Published: (2025)

ACAVCaps: Enabling large-scale training for fine-grained and diverse audio understanding
by: Niu, Yadong, et al.
Published: (2026)

Enhancing Automated Audio Captioning via Large Language Models with Optimized Audio Encoding
by: Liu, Jizhong, et al.
Published: (2024)

Efficient Speech Enhancement via Embeddings from Pre-trained Generative Audioencoders
by: Sun, Xingwei, et al.
Published: (2025)

Bridging Language Gaps in Audio-Text Retrieval
by: Yan, Zhiyong, et al.
Published: (2024)

DashengTokenizer: One layer is enough for unified audio understanding and generation
by: Dinkel, Heinrich, et al.
Published: (2026)

The Interspeech 2026 Audio Encoder Capability Challenge for Large Audio Language Models
by: Dinkel, Heinrich, et al.
Published: (2026)

The ICME 2025 Audio Encoder Capability Challenge
by: Zhang, Junbo, et al.
Published: (2025)

Streaming Audio Transformers for Online Audio Tagging
by: Dinkel, Heinrich, et al.
Published: (2023)

Enhancing Temporal Understanding in Audio Question Answering for Large Audio Language Models
by: Sridhar, Arvind Krishna, et al.
Published: (2024)

Data-Balanced Curriculum Learning for Audio Question Answering
by: Wijngaard, Gijs, et al.
Published: (2025)

Scaling up masked audio encoder learning for general audio classification
by: Dinkel, Heinrich, et al.
Published: (2024)

Improving Audio Question Answering with Variational Inference
by: Chen, Haolin
Published: (2026)

Towards Spatial Audio Understanding via Question Answering
by: Sudarsanam, Parthasaarathy, et al.
Published: (2025)

StarVC: A Unified Auto-Regressive Framework for Joint Text and Speech Generation in Voice Conversion
by: Li, Fengjin, et al.
Published: (2025)

Braille-to-Speech Generator: Audio Generation Based on Joint Fine-Tuning of CLIP and Fastspeech2
by: Xu, Chun, et al.
Published: (2024)

Analytic Study of Text-Free Speech Synthesis for Raw Audio using a Self-Supervised Learning Model
by: Park, Joonyong, et al.
Published: (2024)

Omni-R1: Do You Really Need Audio to Fine-Tune Your Audio LLM?
by: Rouditchenko, Andrew, et al.
Published: (2025)

Improving Code Switching with Supervised Fine Tuning and GELU Adapters
by: Pham, Linh
Published: (2025)

Leveraging Chain of Thought towards Empathetic Spoken Dialogue without Corresponding Question-Answering Data
by: Xie, Jingran, et al.
Published: (2025)

Fine-Tuning MIDI-to-Audio Alignment using a Neural Network on Piano Roll and CQT Representations
by: Murgul, Sebastian, et al.
Published: (2025)

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation
by: Mu, Zhaoxi, et al.
Published: (2025)

Improving Audio Captioning Models with Fine-grained Audio Features, Text Embedding Supervision, and LLM Mix-up Augmentation
by: Wu, Shih-Lun, et al.
Published: (2023)

SAFE-QAQ: End-to-End Slow-Thinking Audio-Text Fraud Detection via Reinforcement Learning
by: Wang, Peidong, et al.
Published: (2026)

Probing for Phonology in Self-Supervised Speech Representations: A Case Study on Accent Perception
by: Venkateswaran, Nitin, et al.
Published: (2025)

Fine-Tuning Large Multimodal Models for Automatic Pronunciation Assessment
by: Wang, Ke, et al.
Published: (2025)

Audio-Thinker: Guiding Audio Language Model When and How to Think via Reinforcement Learning
by: Wu, Shu, et al.
Published: (2025)

Multi-Domain Audio Question Answering Benchmark Toward Acoustic Content Reasoning
by: Yang, Chao-Han Huck, et al.
Published: (2025)

Robust Audio Tagging under Class-wise Supervision Unreliability
by: Hou, Yuanbo, et al.
Published: (2026)

HearFit+: Personalized Fitness Monitoring via Audio Signals on Smart Speakers
by: Xie, Yadong, et al.
Published: (2025)

Is Self-Supervised Learning Enough to Fill in the Gap? A Study on Speech Inpainting
by: Asaad, Ihab, et al.
Published: (2024)

AQAScore: Evaluating Semantic Alignment in Text-to-Audio Generation via Audio Question Answering
by: Kuan, Chun-Yi, et al.
Published: (2026)

The NeurIPS 2023 Machine Learning for Audio Workshop: Affective Audio Benchmarks and Novel Data
by: Baird, Alice, et al.
Published: (2024)

Effective Text Adaptation for LLM-based ASR through Soft Prompt Fine-Tuning
by: Ma, Yingyi, et al.
Published: (2024)

Overcoming Data Scarcity in Multi-Dialectal Arabic ASR via Whisper Fine-Tuning
by: Özyilmaz, Ömer Tarik, et al.
Published: (2025)

Speaker Diarization for Low-Resource Languages Through Wav2vec Fine-Tuning
by: Abdullah, Abdulhady Abas, et al.
Published: (2025)

Self-Supervised Multi-View Learning for Disentangled Music Audio Representations
by: Wilkins, Julia, et al.
Published: (2024)