À propos de ce 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.
946 épisodes · Technologie
AI Post Transformers
Dernier épisodeGraniKV: Asymmetric KV-Cache Paging for Shared-Prefix Agents
À propos de ce 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.
Épisodes récents
- LLMLingua: Compressing Prompts with Small-Model Token Pruningavant-hier
- In-Context Autoencoder: Compressing Long Contexts into Memory Slotsavant-hier
- Attention Sinks Enable Streaming Language Models Over Endless Inputavant-hier
- Speculative Prefill: Training-Free Token Importance for Faster TTFTavant-hier
- Memory Layers at Scale: Trainable Key-Value Lookup for Factsil y a 3 jours
- Jenga: Two-Level Memory Allocation for Heterogeneous LLM Servingil y a 3 jours
- AttnComp: Attention-Guided Adaptive Context Compression for RAGil y a 3 jours
- LongAttnComp: Cross-Family Context Compression for Long-Context Reasoningil y a 3 jours
- MLCommons Chakra: Standardized Execution Traces for AI Benchmarking and Co-designil y a 3 jours
- Product Keys Give Transformers Million-Slot Memory Layersil y a 3 jours
podlinkr.com/fr/ai-post-transformers
Pour une affiche ou une diapo.