ICLR Poster No Need to Talk: Asynchronous Mixture of Language ModelsICLR 2025

3/3

Mixture of experts on high latency networks with No Need to Talk iclr.cc/virtual/2025... (Thu Apr 24 3pm).

Joint work with @matpagliardini.bsky.social , Anastasiia Filippova, @pierreablin.bsky.social, Simin Fan, Skyler Seto, Angelos Katharopoulos, Ronan Collobert

21.04.2025 23:54 — 👍 0    🔁 0    💬 0    📌 0

ICLR Poster Task-Adaptive Pretrained Language Models via Clustered-Importance SamplingICLR 2025

2/3

Importance sampling for better pretraining distribution with CRISP iclr.cc/virtual/2025... (Sat Apr 26, 10 am).

21.04.2025 23:54 — 👍 1    🔁 0    💬 1    📌 0

#ICLR #TrainBetterLM I am at ICLR, come to our posters for improved language model training!

Recycle gradients for faster neural net training with AdEMAmix iclr.cc/virtual/2025... (Fri Apr 25, 10 am).

1/3

21.04.2025 23:54 — 👍 2    🔁 3    💬 1    📌 0