pith. sign in

Micha{\l} Krutul

Identifiers

  • name variant Micha{\l} Krutul 0.60 · backfill

Papers (6)

  1. Decoupled Relative Learning Rate Schedules cs.LG · 2025 · author #4
  2. Projected Compression: Trainable Projection for Efficient Transformer Compression cs.LG · 2025 · author #2
  3. Joint MoE Scaling Laws: Mixture of Experts Can Be Memory Efficient cs.LG · 2025 · author #5
  4. Scaling Laws for Fine-Grained Mixture of Experts cs.LG · 2024 · author #5
  5. MoE-Mamba: Efficient Selective State Space Models with Mixture of Experts cs.LG · 2024 · author #5
  6. Mixture of Tokens: Continuous MoE through Cross-Example Aggregation cs.CL · 2023 · author #2

Mentions

  • 2507.03526 #4 · arxiv_oai · confidence 0.70 Micha{\l} Krutul
  • 2506.22255 #2 · arxiv_oai · confidence 0.70 Micha{\l} Krutul
  • 2502.05172 #5 · arxiv_oai · confidence 0.70 Micha{\l} Krutul
  • 2310.15961 #2 · arxiv_oai · confidence 0.70 Micha{\l} Krutul
  • 2401.04081 #5 · arxiv_oai · confidence 0.70 Micha{\l} Krutul
  • 2402.07871 #5 · arxiv_oai · confidence 0.70 Micha{\l} Krutul

Frequent Coauthors