pith. sign in

Sebastian Jaszczur

Identifiers

  • name variant Sebastian Jaszczur 0.60 · backfill

Papers (9)

  1. Decoupled Relative Learning Rate Schedules cs.LG · 2025 · author #11
  2. Projected Compression: Trainable Projection for Efficient Transformer Compression cs.LG · 2025 · author #6
  3. Joint MoE Scaling Laws: Mixture of Experts Can Be Memory Efficient cs.LG · 2025 · author #11
  4. Scaling Laws for Fine-Grained Mixture of Experts cs.LG · 2024 · author #12
  5. MoE-Mamba: Efficient Selective State Space Models with Mixture of Experts cs.LG · 2024 · author #10
  6. Structured Packing in LLM Training Improves Long Context Utilization cs.CL · 2023 · author #3
  7. Mixture of Tokens: Continuous MoE through Cross-Example Aggregation cs.CL · 2023 · author #10
  8. Sparse is Enough in Scaling Transformers cs.LG · 2021 · author #1
  9. Neural heuristics for SAT solving cs.AI · 2020 · author #1

Mentions

  • 2507.03526 #11 · arxiv_oai · confidence 0.70 Sebastian Jaszczur
  • 2506.22255 #6 · arxiv_oai · confidence 0.70 Sebastian Jaszczur
  • 2312.17296 #3 · arxiv_oai · confidence 0.70 Sebastian Jaszczur
  • 2502.05172 #11 · arxiv_oai · confidence 0.70 Sebastian Jaszczur
  • 2310.15961 #10 · arxiv_oai · confidence 0.70 Sebastian Jaszczur
  • 2401.04081 #10 · arxiv_oai · confidence 0.70 Sebastian Jaszczur
  • 2402.07871 #12 · arxiv_oai · confidence 0.70 Sebastian Jaszczur
  • 2111.12763 #1 · arxiv_oai · confidence 0.70 Sebastian Jaszczur
  • 2005.13406 #1 · arxiv_oai · confidence 0.70 Sebastian Jaszczur

Frequent Coauthors