Chih-Kai Yang

zenyn's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper about 10 hours ago

Nudging Hidden States: Training-Free Model Steering for Chain-of-Thought Reasoning in Large Audio-Language Models

Paper • 2603.14636 • Published 13 days ago • 1

submitted a paper to Daily Papers 1 day ago

Nudging Hidden States: Training-Free Model Steering for Chain-of-Thought Reasoning in Large Audio-Language Models

Paper • 2603.14636 • Published 13 days ago • 1

authored 3 papers 1 day ago

A Preliminary Exploration with GPT-4o Voice Mode

Paper • 2502.09940 • Published Feb 14, 2025

MUGEN: Evaluating and Improving Multi-audio Understanding of Large Audio-Language Models

Paper • 2603.09714 • Published 18 days ago

Nudging Hidden States: Training-Free Model Steering for Chain-of-Thought Reasoning in Large Audio-Language Models

Paper • 2603.14636 • Published 13 days ago • 1

updated 4 datasets about 2 months ago

Multi-Audio-Grounding/Dysarthria_Detection

Viewer • Updated Feb 5 • 200 • 40

Multi-Audio-Grounding/Duration_Precise_Selection

Viewer • Updated Feb 5 • 150 • 55

Multi-Audio-Grounding/Duration_Ordinal_Selection

Viewer • Updated Jan 30 • 50 • 30

Multi-Audio-Grounding/Duration_Extremes_Extraction

Viewer • Updated Feb 5 • 200 • 38

published a dataset 2 months ago

Multi-Audio-Grounding/Dysarthria_Detection

Viewer • Updated Feb 5 • 200 • 40

liked a dataset 2 months ago

amaai-lab/DisfluencySpeech

Viewer • Updated Jun 27, 2024 • 5k • 309 • 19

published 3 datasets 2 months ago

Multi-Audio-Grounding/Duration_Precise_Selection

Viewer • Updated Feb 5 • 150 • 55

Multi-Audio-Grounding/Duration_Ordinal_Selection

Viewer • Updated Jan 30 • 50 • 30

Multi-Audio-Grounding/Duration_Extremes_Extraction

Viewer • Updated Feb 5 • 200 • 38

upvoted a paper 5 months ago

Pseudo2Real: Task Arithmetic for Pseudo-Label Correction in Automatic Speech Recognition

Paper • 2510.08047 • Published Oct 9, 2025 • 8

upvoted a collection 5 months ago

Awesome papers from 臺大李宏毅 (Hung-yi Lee)

Collection

Recent papers authored by Hung-yi Lee. Sorted by ID • 8 items • Updated Oct 24, 2025 • 17

upvoted a paper 5 months ago

SAKE: Towards Editing Auditory Attribute Knowledge of Large Audio-Language Models

Paper • 2510.16917 • Published Oct 19, 2025 • 20

commented a paper 5 months ago

SAKE: Towards Editing Auditory Attribute Knowledge of Large Audio-Language Models

Paper • 2510.16917 • Published Oct 19, 2025 • 20 •

2

upvoted a paper 5 months ago

Investigating Safety Vulnerabilities of Large Audio-Language Models Under Speaker Emotional Variations

Paper • 2510.16893 • Published Oct 19, 2025 • 18

commented a paper 5 months ago

Investigating Safety Vulnerabilities of Large Audio-Language Models Under Speaker Emotional Variations

Paper • 2510.16893 • Published Oct 19, 2025 • 18 •

2