Paul Janson

Pauljanson002's activity

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

upvoted 3 papers about 1 month ago

Heterogeneous Low-Bandwidth Pre-Training of LLMs

Paper • 2601.02360 • Published Jan 5 • 2

A Simple Baseline that Questions the Use of Pretrained-Models in Continual Learning

Paper • 2210.04428 • Published Oct 10, 2022 • 2

Overcoming Generic Knowledge Loss with Selective Parameter Update

Paper • 2308.12462 • Published Aug 23, 2023 • 1

upvoted a paper 2 months ago

PyLO: Towards Accessible Learned Optimizers in PyTorch

Paper • 2506.10315 • Published Jun 12, 2025 • 2

upvoted a paper over 1 year ago

Beyond Cosine Decay: On the effectiveness of Infinite Learning Rate Schedule for Continual Pre-training

Paper • 2503.02844 • Published Mar 4, 2025 • 1

upvoted a paper about 2 years ago

μLO: Compute-Efficient Meta-Generalization of Learned Optimizers

Paper • 2406.00153 • Published May 31, 2024 • 13