#machinelearning

@tin_rabzelj Ring Attention with Blockwise Transformers for Near-Infinite Context | Paper Notes #AI #MachineLearning #DeepLearning

@tin_rabzelj GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints | Paper Notes #AI #MachineLearning #Research

@tin_rabzelj Fast Transformer Decoding: One Write-Head is All You Need | Paper Notes #AI #MachineLearning #NLP

@tin_rabzelj Fast Inference from Transformers via Speculative Decoding | Paper Notes #AI #MachineLearning #Inference

@shekhar_gulati Notes from Gemini Embedding Paper #GenerativeAI #MachineLearning #Research

@tin_rabzelj Effective Long-Context Scaling of Foundation Models | Paper Notes #AI #MachineLearning #Research

@joel_grus Vibe Coding 9 -- AI Agents That Play Taboo #AI #MachineLearning #NLP

@etsy_code_as_craft Building Etsy Buyer Profiles with LLMs #AI #MachineLearning #DataScience

@etsy_code_as_craft Building Etsy Buyer Profiles with LLMs #AI #MachineLearning #DataScience

@etsy_code_as_craft Building Etsy Buyer Profiles with LLMs #AI #MachineLearning #DataScience

@tin_rabzelj Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention | Paper Notes #AI #MachineLearning #DeepLearning

@tin_rabzelj Longformer: The Long-Document Transformer | Paper Notes #AI #MachineLearning #NLP

@tin_rabzelj FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness | Paper Notes #AI #MachineLearning #DeepLearning

@tin_rabzelj Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation | Paper Notes #AI #MachineLearning #DeepLearning

@tin_rabzelj The Impact of Positional Encoding on Length Generalization in Transformers | Paper Notes #AI #MachineLearning #NLP

@tin_rabzelj RoFormer: Enhanced Transformer with Rotary Position Embedding | Paper Notes #AI #MachineLearning #NLP

@tin_rabzelj ReAct: Synergizing Reasoning and Acting in Language Models | Paper Notes #AI #MachineLearning #Research

@joel_grus Vibe Coding 8 -- Clod Code #SoftwareEngineering #DataScience #MachineLearning

@shrivus_substack Betting Against the Models #AI #MachineLearning #SoftwareEngineering

@tin_rabzelj Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer | Paper Notes #AI #MachineLearning #DeepLearning

@tin_rabzelj Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer | Paper Notes #AI #MachineLearning #DeepLearning

@tin_rabzelj Language Models are Few-Shot Learners | Paper Notes #AI #MachineLearning #Research

@tin_rabzelj Language Models are Unsupervised Multitask Learners | Paper Notes #AI #MachineLearning #NLP

@fin_ai_research We Don't Need Higher Peak Intelligence, Only More Intelligence Density #AI #MachineLearning #Research

@laurens_data_substack What the Final Score Didn't Tell You: The 2025 Women's Final in Football Analytics #DataScience #MachineLearning #SportsAnalytics

@synced Which Agent Causes Task Failures and When?Researchers from PSU and Duke explores automated failure attribution of LLM Multi-Agent Systems #AI #MachineLearning #LLM

@tin_rabzelj Improving Language Understanding by Generative Pre-Training | Paper Notes #AI #MachineLearning #NLP

@ezyangs_blog State of torch.compile for training (August 2025) #PyTorch #MachineLearning #OpenSource

@joel_grus Vibe Coding 7 -- Human in the Loop as a dspy.Tool #AI #MachineLearning #SoftwareEngineering

@tin_rabzelj Attention Is All You Need | Paper Notes #AI #MachineLearning #DeepLearning

@joel_grus Vibe Coding 5 -- WoDRAG #SoftwareEngineering #DataScience #MachineLearning

@tin_rabzelj Neural Machine Translation by Jointly Learning to Align and Translate | Paper Notes #AI #MachineLearning #NLP

@fin_ai_research Fin: Running a Reliable Service over Unreliable Parts #AI #MachineLearning #Reliability

@tin_rabzelj Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference | Paper Notes #AI #MachineLearning #DeepLearning

@tin_rabzelj Sequence to Sequence Learning with Neural Networks | Paper Notes #AI #MachineLearning #DeepLearning

@joel_grus Vibe Coding 3 -- Simple Chatbots in DSPy #AI #MachineLearning #DSPy

@tin_rabzelj GloVe: Global Vectors for Word Representation | Paper Notes #AI #NLP #MachineLearning

@max_woolfs_blog LLMs can now identify public figures in images #AI #MachineLearning #ComputerVision

@piotr_migdal Which chart would you swipe right? #DataViz #MachineLearning #AI

@joel_grus Vibe Coding 2 -- SnowMeth - an AI Novel-Writing Assistant #AI #MachineLearning #Writing