Chao-Han Huck Yang

Researcher@NVIDIA Research·中国台湾·OpenReview

研究方向

Machine Translation · Multilingual Language Modeling · Time Series · Quantum Machine Learning · Causal Inference · Deep Reinforcement Learning · Language Modeling · Speech Recognition · Neuroevolution · Adversarial Robustness · Speech Enhancement · Online Optimization

Chao-Han Huck Yang

Test-Time Alignment for Large Language Models via Textual Model Predictive Control

UALM: Unified Audio Language Model for Understanding, Generation and Reasoning

OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM

TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models

Long Grounded Thoughts: Distilling Compositional Visual Reasoning Chains at Scale

Estimating Time Series Foundation Model Transferability via In-Context Learning

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

Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models

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

Audio Large Language Models Can Be Descriptive Speech Quality Evaluators

Fugatto 1: Foundational Generative Audio Transformer Opus 1

Towards Neural Scaling Laws for Time Series Foundation Models

A Quantum Circuit-Based Compression Perspective for Parameter-Efficient Learning

Reinforcement Learning Enhanced Full-Duplex Spoken Dialogue Language Models for Conversational Interactions

UniWav: Towards Unified Pre-training for Speech Representation Learning and Generation

OWLS: Scaling Laws for Multilingual Speech Recognition and Translation Models

VoiceNoNG: High-Quality Speech Editing Model without Hallucinations