National Taiwan University

university

Verified

https://www.ntu.edu.tw

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

voidism authored a paper 11 days ago

World of SWECraft: Agent Collaboration at Scale via Simulated Software Worlds

47z submitted a paper about 1 month ago

Rethinking Automated Voice Similarity by Shifting from EER to Embedding Geometry

kehanlu submitted a paper 7 months ago

How Auditory Knowledge in LLM Backbones Shapes Audio Language Models: A Holistic Evaluation

View all activity

Papers

Rethinking Automated Voice Similarity by Shifting from EER to Embedding Geometry

FdAudio: MeanFlow-Anchored Fréchet-Distance Post-Training for One-Step Text-to-Audio Generation

View all Papers

authored a paper 11 days ago

World of SWECraft: Agent Collaboration at Scale via Simulated Software Worlds

Paper • 2610.24061 • Published 19 days ago • 8

47z

submitted a paper to Daily Papers about 1 month ago

Rethinking Automated Voice Similarity by Shifting from EER to Embedding Geometry

Paper • 2609.33999 • Published Sep 27 • 6

47z

submitted a paper to Daily Papers 7 months ago

MoVE: Translating Laughter and Tears via Mixture of Vocalization Experts in Speech-to-Speech Translation

Paper • 2604.17435 • Published Apr 19 • 2

47z

authored 2 papers 7 months ago

TAU: A Benchmark for Cultural Sound Understanding Beyond Semantics

Paper • 2509.26329 • Published Sep 30, 2025 • 3

MoVE: Translating Laughter and Tears via Mixture of Vocalization Experts in Speech-to-Speech Translation

Paper • 2604.17435 • Published Apr 19 • 2

submitted a paper to Daily Papers 7 months ago

How Auditory Knowledge in LLM Backbones Shapes Audio Language Models: A Holistic Evaluation

Paper • 2603.19195 • Published Mar 19 • 3

submitted a paper to Daily Papers 7 months ago

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

Paper • 2603.14636 • Published Mar 15 • 3

authored 3 papers about 1 year ago

Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks

Paper • 2411.05361 • Published Nov 8, 2024 • 6

DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment

Paper • 2507.02768 • Published Jul 3, 2025 • 19

Game-Time: Evaluating Temporal Dynamics in Spoken Language Models

Paper • 2509.26388 • Published Sep 30, 2025 • 27

authored a paper about 1 year ago

CoachMe: Decoding Sport Elements with a Reference-Based Coaching Instruction Generation Model

Paper • 2509.11698 • Published Sep 15, 2025 • 1

authored 2 papers over 1 year ago

MetaCLIP 2: A Worldwide Scaling Recipe

Paper • 2507.22062 • Published Jul 29, 2025 • 38

Don't "Overthink" Passage Reranking: Is Reasoning Truly Necessary?

Paper • 2505.16886 • Published May 22, 2025 • 6

authored 7 papers about 2 years ago

Natural Language Embedded Programs for Hybrid Language Symbolic Reasoning

Paper • 2309.10814 • Published Sep 19, 2023 • 3

Interpretable Unified Language Checking

Paper • 2304.03728 • Published Apr 7, 2023

SAIL: Search-Augmented Instruction Learning

Paper • 2305.15225 • Published May 24, 2023 • 2

What makes multilingual BERT multilingual?

Paper • 2010.10938 • Published Oct 20, 2020

SUPERB: Speech processing Universal PERformance Benchmark

Paper • 2105.01051 • Published May 3, 2021 • 1

DUAL: Discrete Spoken Unit Adaptive Learning for Textless Spoken Question Answering

Paper • 2203.04911 • Published Mar 9, 2022

Curiosity-driven Red-teaming for Large Language Models

Paper • 2402.19464 • Published Feb 29, 2024 • 1