Eric Xian

ericxian1997's activity

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

upvoted a paper 12 days ago

Joint Selection for Large-Scale Pre-Training Data via Policy Gradient-based Mask Learning

Paper • 2512.24265 • Published Dec 30, 2025 • 4

upvoted a collection 13 days ago

UltraData

Collection

Ultra Scale, Ultra Quality, Ultra Coverage • 9 items • Updated 14 days ago • 77

upvoted a paper 3 months ago

Virtual Width Networks

Paper • 2511.11238 • Published Nov 14, 2025 • 38

upvoted a paper 4 months ago

Does your data spark joy? Performance gains from domain upsampling at the end of training

Paper • 2406.03476 • Published Jun 5, 2024 • 4

upvoted a collection 5 months ago

DeepSeek-V3.2

Collection

4 items • Updated Dec 1, 2025 • 528

upvoted a paper 11 months ago

MAGA: MAssive Genre-Audience Reformulation to Pretraining Corpus Expansion

Paper • 2502.04235 • Published Feb 6, 2025 • 23