Agentic pipelines: Reasoning & Retrieval // Multi-agent approachMulti-agent reasoning: classification, planning, CoT, code/query generation & execution, tools use, memories, internal/external sources…13h ago13h ago
New Lightning Attention Architecture LLM // 1st production modelUp to 4M context // open source6d ago6d ago
Physical AI // next frontier of AI, text2world modelsWhen will autonomous robots walk among us? // a lot of work for labelers to label the world(s)Jan 12Jan 12
Search and Retrieval: Not Actual Reasoning // Why Reasoning is hard for computers?Large Reasoning Models (LRMs) actually are Large Retrieval Models of pre-trained knowledgeJan 10Jan 10
AI Generated Realistic Influencers / Avatars & Robots // 2025 trendsDigital dystopia is coming // Digital Avatars and Robots almost already hereJan 9Jan 9
Advanced LLM-based Reasoning // so close to truly intelligent systemsCurious how advanced oX-models work? // let’s see what “more compute” can do?Jan 4Jan 4
In-context Continual Learning LLM // Beyond RAGLLM/ML problems (hallucinations): catastrophic forgetting (FT), Bad RAG accuracy & security (in case of external APIs)Dec 29, 2024Dec 29, 2024
Effective AI Agents // How Close Are We to Full Autonomy?People envision sci-fi-like autonomous AI agents, but for now, we are only taking the first steps toward autonomy with LLM-in-the-loop…Dec 28, 2024Dec 28, 2024
