Vishal RajputinAIGuysThe Fastest Way To Deploy AI ModelsAlthough Modal is not extensive as other cloud-like GCP and AWS, it gets the job done for AI apps.2d ago2d ago
Vishal RajputinAIGuysLLM-based AGI: 50% on the ARC-AGI?ARC-AGI. LLM-Modulo Framework and Planning/Reasoning Capabilities.5d ago15d ago1
Vishal RajputinAIGuysTextGrad: Controlling LLM Behavior Via TextTextGrad backpropagates textual feedback provided by LLMs to improve individual components of a compound AI system.Jun 193Jun 193
Vishal RajputinAIGuysGraph RAG: From Local to GlobalA Graph RAG Approach to Query-Focused SummarizationJun 17Jun 17
Vishal RajputinAIGuysClaude 3: Extracting Interpretable FeaturesDecoding Black Box Nature of Transformer-based ModelJun 101Jun 101
Vishal RajputinAIGuysAIGuys Digest🌟 Welcome to the AIGuys Digest Newsletter, where we cover State-of-the-Art AI breakthroughs and all the major AI news🚀Jun 3Jun 3
Vishal RajputinAIGuysPrompt Engineering Is Dead: DSPy Is New Paradigm For PromptingDSPy Paradigm: Let’s program — not prompt — LLMsMay 2934May 2934
Vishal RajputinAIGuysYOLOv10: Object Detection King Is BackSpeed, Speed, Speed. This is what YOLOv10 is all about, faster InferenceMay 273May 273
Vishal RajputinAIGuysxLSTM vs. Transformers: Who Will Win?xLSTM revives the age old LSTM with incorporating features from Transformers, making it a serious competitor in the LLM race.May 222May 222
Vishal RajputinAIGuysMoE and LLM Merging RecipesNext step for LLM Mixture of Experts, Evolutionary model merging?May 15May 15