Stay curious. Keep exploring.

AGI research learning notes and work explainers.

Driven by AGI curiosity and mission: my papers, projects, and learning notes.

All Research

2 entries

Pinned Paper Explainer · P1

Can We Train an MoE Model with the Same Total Parameters and Performance as Dense?

An ICLR 2026 Oral paper explainer: MoE needs a more aggressive data scaling strategy.

MoEPretrainLLMICLR 2026 oralData ScalingData Reuse

May 8, 202630 min read Read note

Can We Train an MoE Model with the Same Total Parameters and Performance as Dense? figure

Appendix: Can We Train an MoE Model with the Same Total Parameters and Performance as Dense?

An ICLR 2026 Oral paper explainer: MoE needs a more aggressive data scaling strategy.

MoEPretrainLLMICLR 2026 oralData ScalingData ReuseAPPENDIX

May 8, 202625 min read Read note

Appendix: Can We Train an MoE Model with the Same Total Parameters and Performance as Dense? figure

No posts for this topic.

Choose another topic or return to the full research flow.

You're all caught up. More research to come.