Xiliang Yang's picture

2

Xiliang Yang

NoManDeRY

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 29 days ago

MOOSE-Star: Unlocking Tractable Training for Scientific Discovery by Breaking the Complexity Barrier

authored a paper about 1 year ago

DPO-Shift: Shifting the Distribution of Direct Preference Optimization

updated a model about 1 year ago

NoManDeRY/DPO-Shift-Llama-3-8B-Ultrafeedback-fixed-0.95

View all activity

Organizations

None yet

Papers 1

arxiv:2502.07599

models 7

NoManDeRY/DPO-Shift-Llama-3-8B-Ultrafeedback-fixed-0.95

Text Generation • 8B • Updated Feb 18, 2025 • 4

NoManDeRY/DPO-Shift-Llama-3-8B-Ultrafeedback-decrease_linear-1.0to0.95

Text Generation • 8B • Updated Feb 18, 2025 • 3

NoManDeRY/DPO-Shift-Llama-3-8B-Ultrafeedback-increase_linear_0.95to1.0

Text Generation • 8B • Updated Feb 18, 2025 • 2

NoManDeRY/DPO-Shift-Qwen-2-7B-Ultrafeedback-fixed-1.0

Text Generation • 8B • Updated Feb 18, 2025 • 3

NoManDeRY/DPO-Shift-Qwen-2-7B-Ultrafeedback-fixed-0.95

Text Generation • 8B • Updated Feb 18, 2025 • 1

NoManDeRY/DPO-Shift-Qwen-2-7B-UltraChat200K-SFT

Text Generation • 8B • Updated Feb 18, 2025 • 1

NoManDeRY/DPO-Shift-Llama-3-8B-Ultrafeedback-fixed-1.0

Text Generation • 8B • Updated Feb 18, 2025 • 5

datasets 0

None public yet