Tzu-Han Lin's picture

1 1 70

Tzu-Han Lin

hank0316

·

AI & ML interests

Large Language Model, Evaluation, Parameter-Efficient Fine-Tuning (PEFT)

Recent Activity

upvoted a paper 6 days ago

STITCH: Simultaneous Thinking and Talking with Chunked Reasoning for Spoken Language Models

liked a model 3 months ago

GAIR/ToRL-7B

updated a model 3 months ago

hank0316/Qwen2.5-7B-MATH-Iter1-Epoch2

View all activity

Organizations

authored 2 papers about 1 year ago

PEFT for Speech: Unveiling Optimal Placement, Merging Strategies, and Ensemble Techniques

Paper • 2401.02122 • Published Jan 4, 2024 • 2

DogeRM: Equipping Reward Models with Domain Knowledge through Model Merging

Paper • 2407.01470 • Published Jul 1, 2024 • 6