Egor Petrov

moderntalker's activity

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

authored a paper 2 days ago

One-Step Gradient Delay is Not a Barrier for Large-Scale Asynchronous Pipeline Parallel LLM Pretraining

Paper • 2606.30634 • Published 5 days ago • 23

upvoted a paper 3 days ago

One-Step Gradient Delay is Not a Barrier for Large-Scale Asynchronous Pipeline Parallel LLM Pretraining

Paper • 2606.30634 • Published 5 days ago • 23

updated a model 4 days ago

moderntalker/efficient_pretrain_checkpoints

Updated 3 days ago

published a model about 2 months ago

moderntalker/efficient_pretrain_checkpoints

Updated 3 days ago

liked a model 2 months ago

deepseek-ai/DeepSeek-V4-Pro

Text Generation • 862B • Updated 11 days ago • 1.18M • 5.14k

upvoted a paper 3 months ago

Reasoning Shift: How Context Silently Shortens LLM Reasoning

Paper • 2604.01161 • Published Apr 1 • 32