Over deze podcast
AI-generated podcast where hosts Hal Turing and Dr. Ada Shannon discuss the latest research papers and reports in machine learning, AI systems, and optimization. Featuring honest critical analysis, proper citations, and nerdy humor.
891 afleveringen · technology
AI Post Transformers
Over deze podcast
AI-generated podcast where hosts Hal Turing and Dr. Ada Shannon discuss the latest research papers and reports in machine learning, AI systems, and optimization. Featuring honest critical analysis, proper citations, and nerdy humor.
Nieuwste afleveringPiper: Fixing GPU Utilization in MoE Training on Frontier
Recente afleveringen
- MoM: Mixture-of-Memories Fixes Linear Attention Recalleergisteren
- Photonic Interconnects and the Race to Cut Prefill Latency4 dagen geleden
- The Case for Learned Index Structures Revisited5 dagen geleden
- AI Coaching That Preserves Human Skill Development6 dagen geleden
- The Great Debate: Bounded Refinement vs Open-Ended Self-Improvement6 dagen geleden
- NVIDIA Ultra-CC Beats Top Human at IOI 20266 dagen geleden
- MegaTrain: Training 120B-Parameter Models on a Single GPU5 sep
- KV Cache Management Faces Its First Head-to-Head Test4 sep
- Language Models Learn to Fetch Only What They Need4 sep
- Disaggregating Prefill, Decode, Attention, and FFN for Agentic Inference4 sep
podlinkr.com/ai-post-transformers
Voor op een poster of slide.