Aidan Scannell
banner
aidanscannell.bsky.social
Aidan Scannell
@aidanscannell.bsky.social
AI/ML/Robotics. Incoming postdoc at University of Edinburgh, previously at Aalto University.
Reposted by Aidan Scannell
Our #ICLR2025 poster "Discrete Codebook World Models for Continuous Control" (Aidan Scannell, Mohammadreza Nakhaeinezhadfard, Kalle Kujanpää, Yi Zhao, Kevin Luck, Arno Solin, Joni Pajarinen)
🗓️ Hall 3 + Hall 2B #415, Thu 24 Apr 10 a.m. +08 — 12:30 p.m. +08
📄 Preprint: arxiv.org/abs/2503.00653
April 21, 2025 at 3:38 PM
Reposted by Aidan Scannell
Multi-Head Latent Attention vs Group Query Attention: We break down why MLA is a more expressive memory compression technique AND why naive implementations can backfire. Check it out!
⚡️Multi-Head Latent Attention is one of the key innovations that enabled @deepseek_ai's V3 and the subsequent R1 model.

⏭️ Join us as we continue our series into efficient AI inference, covering both theoretical insights and practical implementation:

🔗 datacrunch.io/blog/deepsee...
DeepSeek + SGLang: Multi-Head Latent Attention
Multi-Head Latent Attention (MLA) improves upon Group Query Attention (GQA), enabling long-context reasoning models and wider adoption across open-source LLMs.
datacrunch.io
March 12, 2025 at 7:01 PM