Tianjin Huang

TianjinHuang's activity

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

upvoted a paper 13 days ago

Stable-SPAM: How to Train in 4-Bit More Stably than 16-Bit Adam

Paper • 2502.17055 • Published 14 days ago • 16

upvoted a paper about 2 months ago

SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training

Paper • 2501.06842 • Published Jan 12 • 15

upvoted a paper 3 months ago

APOLLO: SGD-like Memory, AdamW-level Performance

Paper • 2412.05270 • Published Dec 6, 2024 • 38