https://ramdi.fr/tags/machine-learning/Recent content in Machine-Learning on Noureddine RAMDIHugoenSat, 23 May 2026 20:41:27 +0000https://ramdi.fr/github-stars/ai-interview-codex-iterative-ai-system-design-and-interview-prep-with-real-world-benchmarks/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/ai-interview-codex-iterative-ai-system-design-and-interview-prep-with-real-world-benchmarks/ai-interview-codex offers a practical AI interview prep guide featuring iterative system design for Agentic AI and RAG, with benchmarks and production insights for ML, LLM, and system design roles.https://ramdi.fr/github-stars/ai-ml-cheatsheets-a-structured-collection-of-ai-and-machine-learning-reference-sheets/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/ai-ml-cheatsheets-a-structured-collection-of-ai-and-machine-learning-reference-sheets/AI-ML-Cheatsheets offers a modular, offline-ready collection of concise AI/ML reference sheets from foundational math to transformers and large language models.https://ramdi.fr/github-stars/autodistill-automating-vision-model-distillation-from-foundation-models-to-edge-deployables/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/autodistill-automating-vision-model-distillation-from-foundation-models-to-edge-deployables/Autodistill automates the pipeline from large foundation models to edge-ready vision models using pluggable plugins and a natural language ontology for zero-shot labeling.https://ramdi.fr/github-stars/bytez-unified-serverless-inference-across-220000-ai-models-with-a-single-api/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/bytez-unified-serverless-inference-across-220000-ai-models-with-a-single-api/Bytez offers a unified API for over 220,000 AI models with serverless GPU orchestration, abstracting model diversity into a single inference platform accessible via one key.https://ramdi.fr/github-stars/deepspeed-scalable-deep-learning-optimization-with-extensible-hardware-support/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/deepspeed-scalable-deep-learning-optimization-with-extensible-hardware-support/DeepSpeed is a Python library that optimizes large-scale deep learning training with multi-hardware support and JIT CUDA extensions. Explore its architecture, strengths, and quick installation.https://ramdi.fr/github-stars/fast3r-scalable-multi-view-3d-reconstruction-with-a-single-forward-pass/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/fast3r-scalable-multi-view-3d-reconstruction-with-a-single-forward-pass/Fast3R from Meta FAIR processes 1000+ unordered images simultaneously for 3D reconstruction using a ViT-Large backbone and multi-view attention, eliminating iterative matching.https://ramdi.fr/github-stars/gnnpapers-the-definitive-curated-reading-list-for-graph-neural-network-research/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/gnnpapers-the-definitive-curated-reading-list-for-graph-neural-network-research/gnnpapers is a curated, community-recognized bibliography of 800+ must-read graph neural network papers. It organizes GNN research evolution and applications without any code.https://ramdi.fr/github-stars/inside-mini-sglang-a-clear-and-modular-python-llm-inference-engine/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/inside-mini-sglang-a-clear-and-modular-python-llm-inference-engine/Mini-SGLang is a modular Python reimplementation of the SGLang LLM inference engine with production features like Radix Cache, chunked prefill, overlap scheduling, and tensor parallelism.https://ramdi.fr/github-stars/kimi-audio-a-unified-hybrid-token-audio-foundation-model-with-llm-core/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/kimi-audio-a-unified-hybrid-token-audio-foundation-model-with-llm-core/Kimi-Audio combines continuous acoustic and discrete semantic tokens within a 7B LLM for unified audio-text understanding and generation. It achieves state-of-the-art ASR with low-latency audio synthesis.https://ramdi.fr/github-stars/lynx-modular-personalized-video-generation-with-dual-adapters-on-a-frozen-diffusion-transformer/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/lynx-modular-personalized-video-generation-with-dual-adapters-on-a-frozen-diffusion-transformer/Lynx generates personalized videos from a single image using a frozen Diffusion Transformer with ID and Ref adapters. This modular design balances fidelity and efficiency.https://ramdi.fr/github-stars/mathematics-for-ml-a-curated-guide-to-the-math-behind-machine-learning/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/mathematics-for-ml-a-curated-guide-to-the-math-behind-machine-learning/Mathematics-for-ML is a curated repository aggregating key resources on the mathematical foundations of machine learning. It collects books, papers, and lectures to build strong math intuition for ML practitioners.https://ramdi.fr/github-stars/ml-from-scratch-exploring-machine-learning-fundamentals-with-pure-python-and-numpy/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/ml-from-scratch-exploring-machine-learning-fundamentals-with-pure-python-and-numpy/ML-From-Scratch offers bare-bones Python implementations of key machine learning algorithms using only NumPy, focusing on transparency over efficiency. Explore how it demystifies ML fundamentals.https://ramdi.fr/github-stars/mljobsearch2025-a-compensation-driven-ai-employer-tier-list-and-interview-prep-resource/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/mljobsearch2025-a-compensation-driven-ai-employer-tier-list-and-interview-prep-resource/MLJobSearch2025 offers a curated tier list of AI employers by compensation and a rich set of ML interview questions, helping candidates targeting $300K+ roles prepare effectively.https://ramdi.fr/github-stars/navigating-ai-learning-with-bishwaghimire-s-ai-learning-roadmaps/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/navigating-ai-learning-with-bishwaghimire-s-ai-learning-roadmaps/A practical guide to bishwaghimire’s AI learning roadmaps repository, offering modular, career-focused paths for AI and ML self-learners, with setup essentials and a flexible curriculum.https://ramdi.fr/github-stars/navigating-the-llm-engineer-handbook-a-curated-map-for-production-grade-language-models/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/navigating-the-llm-engineer-handbook-a-curated-map-for-production-grade-language-models/The LLM Engineer Handbook catalogs the full lifecycle of large language model engineering, from pretraining to prompt management, guiding engineers beyond demos to production-ready LLM apps.https://ramdi.fr/github-stars/nougat-vision-transformer-ocr-for-academic-pdfs-extracting-latex-math-and-tables/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/nougat-vision-transformer-ocr-for-academic-pdfs-extracting-latex-math-and-tables/Nougat is Meta’s neural OCR system for academic PDFs, extracting LaTeX math and tables into structured Markdown using a Vision Transformer encoder-decoder. It offers CLI, API, and training tools.https://ramdi.fr/github-stars/overlapnet-siamese-networks-for-loop-closure-detection-in-3d-lidar-slam/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/overlapnet-siamese-networks-for-loop-closure-detection-in-3d-lidar-slam/OverlapNet uses Siamese networks on 2D range images from 3D LiDAR to detect loop closures by predicting overlap and relative yaw angle simultaneously. Practical demos included.https://ramdi.fr/github-stars/safestclaw-a-deterministic-ai-assistant-with-classical-ml-pipelines-for-local-secure-and-zero-cost-operation/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/safestclaw-a-deterministic-ai-assistant-with-classical-ml-pipelines-for-local-secure-and-zero-cost-operation/SafestClaw uses classical ML pipelines and local AI models to deliver 90% of OpenClaw’s features at zero cost, avoiding prompt injection and cloud dependencies.https://ramdi.fr/github-stars/vllm-compressor-practical-quantization-and-compression-for-large-language-model-inference/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/vllm-compressor-practical-quantization-and-compression-for-large-language-model-inference/vLLM Compressor applies advanced quantization and compression techniques to large language models, enabling optimized inference without requiring full model definitions.https://ramdi.fr/github-stars/yue-scalable-dual-track-foundation-model-for-lyrics-to-song-generation/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/yue-scalable-dual-track-foundation-model-for-lyrics-to-song-generation/YuE is an open-source Python foundation model for generating complete songs from lyrics using a two-stage architecture and audio in-context learning. It supports style cloning and LoRA finetuning under Apache 2.0.https://ramdi.fr/github-stars/command-code-an-ai-coding-agent-that-learns-your-coding-taste-with-meta-neuro-symbolic-ai/Tue, 05 May 2026 22:24:55 +0000https://ramdi.fr/github-stars/command-code-an-ai-coding-agent-that-learns-your-coding-taste-with-meta-neuro-symbolic-ai/Command Code uses a meta neuro-symbolic AI ’taste-1’ model to continuously learn and adapt to your coding style, enabling personalized full-stack project building and bug fixing.https://ramdi.fr/github-stars/gomlx-bringing-pytorch-level-machine-learning-to-go-with-openxla-and-wasm/Tue, 05 May 2026 22:24:55 +0000https://ramdi.fr/github-stars/gomlx-bringing-pytorch-level-machine-learning-to-go-with-openxla-and-wasm/GoMLX is a Go-native machine learning framework offering automatic differentiation, multi-backend support including OpenXLA acceleration, and ONNX compatibility. It enables training and inference of LLMs like GPT-2 entirely in Go, with a pure-Go backend for WASM.https://ramdi.fr/github-stars/4dgen-geometry-consistent-multi-view-rgb-d-video-generation-for-robotic-manipulation/Tue, 05 May 2026 13:37:39 +0000https://ramdi.fr/github-stars/4dgen-geometry-consistent-multi-view-rgb-d-video-generation-for-robotic-manipulation/4DGen extends Stable Video Diffusion to generate geometry-consistent multi-view RGB-D videos from single RGB-D inputs using pointmap latents. Trained on multi-view robotic datasets, it enables robot pose extraction from generated videos.https://ramdi.fr/github-stars/action100m-hierarchical-tree-of-captions-for-multi-scale-video-understanding/Tue, 05 May 2026 13:37:39 +0000https://ramdi.fr/github-stars/action100m-hierarchical-tree-of-captions-for-multi-scale-video-understanding/Action100M provides a hierarchical Tree-of-Captions annotation for 100M video segments, enabling multi-scale video understanding with LLM-generated captions. Explore its structure, tech strengths, and how to access the data.https://ramdi.fr/github-stars/alibaba-s-qwen3-6-efficient-large-scale-llms-with-gated-delta-networks-and-sparse-moe/Tue, 05 May 2026 13:37:39 +0000https://ramdi.fr/github-stars/alibaba-s-qwen3-6-efficient-large-scale-llms-with-gated-delta-networks-and-sparse-moe/Qwen3.6 from Alibaba uses gated delta networks and sparse Mixture-of-Experts to achieve near-397B parameter model performance with only 3B active parameters, supporting 201 languages and 262k context length.https://ramdi.fr/github-stars/building-machine-learning-intuition-through-engineering-analogies-with-thereisnospoon/Tue, 05 May 2026 13:37:39 +0000https://ramdi.fr/github-stars/building-machine-learning-intuition-through-engineering-analogies-with-thereisnospoon/There Is No Spoon offers a unique ML primer for software engineers, using physical analogies to build deep intuition for neural networks and architectures beyond memorization.https://ramdi.fr/github-stars/chattts-conversational-text-to-speech-with-prosodic-control-and-responsible-ai-tradeoffs/Tue, 05 May 2026 13:37:39 +0000https://ramdi.fr/github-stars/chattts-conversational-text-to-speech-with-prosodic-control-and-responsible-ai-tradeoffs/ChatTTS is an open-source conversational text-to-speech model trained on 100,000+ hours of bilingual audio. It offers fine-grained prosodic control and employs intentional quality degradation to prevent misuse.https://ramdi.fr/github-stars/curated-machine-learning-video-courses-on-youtube-by-dair-ai-ml-youtube-courses/Tue, 05 May 2026 13:37:39 +0000https://ramdi.fr/github-stars/curated-machine-learning-video-courses-on-youtube-by-dair-ai-ml-youtube-courses/A community-curated list of free machine learning courses on YouTube that organizes and vets educational content for practical learners and enthusiasts.https://ramdi.fr/github-stars/inside-x-s-recommendation-engine-multi-stage-candidate-sourcing-and-neural-ranking/Tue, 05 May 2026 13:37:39 +0000https://ramdi.fr/github-stars/inside-x-s-recommendation-engine-multi-stage-candidate-sourcing-and-neural-ranking/Explore the architecture behind X’s For You Timeline recommendation system, built on Scala, Rust, and advanced ML models. Understand candidate sourcing, neural ranking, and filtering pipelines.https://ramdi.fr/github-stars/machine-learning-interviews-a-structured-guide-for-faang-ml-interview-prep-with-agentic-ai-focus/Tue, 05 May 2026 13:37:39 +0000https://ramdi.fr/github-stars/machine-learning-interviews-a-structured-guide-for-faang-ml-interview-prep-with-agentic-ai-focus/A curated Jupyter notebook guide for machine learning interview prep at FAANG companies, covering coding, system design, and agentic AI systems added in 2025.https://ramdi.fr/github-stars/ovie-monocular-novel-view-synthesis-without-multi-view-supervision/Tue, 05 May 2026 13:37:39 +0000https://ramdi.fr/github-stars/ovie-monocular-novel-view-synthesis-without-multi-view-supervision/OVIE trains novel view synthesis models using unpaired internet images, avoiding the need for calibrated multi-view datasets. It uses Vision Transformers and foundation models for pose and depth encoding.https://ramdi.fr/github-stars/pokieticker-layered-ai-driven-stock-market-analysis-with-sentiment-and-xgboost/Tue, 05 May 2026 13:37:39 +0000https://ramdi.fr/github-stars/pokieticker-layered-ai-driven-stock-market-analysis-with-sentiment-and-xgboost/PokieTicker combines rule-based filtering, LLM sentiment analysis, and XGBoost prediction in a full-stack stock analysis app. Runs locally with no API keys.https://ramdi.fr/github-stars/a-curated-100-day-machine-learning-journey-with-code-and-resources/Mon, 04 May 2026 10:23:03 +0000https://ramdi.fr/github-stars/a-curated-100-day-machine-learning-journey-with-code-and-resources/Explore a 100-day machine learning coding challenge combining classical algorithms, deep learning, and curated resources. A practical, day-by-day learning path for self-directed devs.https://ramdi.fr/github-stars/nvidia-warp-jit-compiling-python-for-cuda-powered-differentiable-physics/Mon, 04 May 2026 10:23:03 +0000https://ramdi.fr/github-stars/nvidia-warp-jit-compiling-python-for-cuda-powered-differentiable-physics/NVIDIA Warp lets you write Python functions JIT-compiled into CUDA kernels for GPU-accelerated differentiable physics and ML integration, simplifying GPU programming in Python.https://ramdi.fr/github-stars/a-curated-gateway-to-machine-learning-resources-for-quantitative-trading/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/a-curated-gateway-to-machine-learning-resources-for-quantitative-trading/A curated GitHub repo consolidates 200+ quality resources for quantitative and ML-driven algorithmic trading, bridging academic research and practical strategies.https://ramdi.fr/github-stars/ai4animation-a-deep-learning-framework-for-neural-character-animation-with-sparse-sensor-control/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/ai4animation-a-deep-learning-framework-for-neural-character-animation-with-sparse-sensor-control/AI4Animation offers a research-driven deep learning framework for neural character animation, enabling real-time control from sparse sensor inputs using categorical codebook matching and periodic autoencoders.https://ramdi.fr/github-stars/apple-silicon-guide-a-comprehensive-developer-reference-for-apple-s-arm-ecosystem/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/apple-silicon-guide-a-comprehensive-developer-reference-for-apple-s-arm-ecosystem/A curated documentation repo for Apple Silicon developers covering chip architectures, dev tools, ML, virtualization, and performance monitoring.https://ramdi.fr/github-stars/davinci-magihuman-simplifying-multimodal-video-and-audio-generation-with-a-single-stream-transformer/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/davinci-magihuman-simplifying-multimodal-video-and-audio-generation-with-a-single-stream-transformer/daVinci-MagiHuman uses a 15B-parameter single-stream transformer with a sandwich architecture to generate video and audio from text, achieving competitive quality and fast inference on a single H100 GPU.https://ramdi.fr/github-stars/dflash-mlx-speculative-decoding-on-apple-silicon-with-metal-and-mlx/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/dflash-mlx-speculative-decoding-on-apple-silicon-with-metal-and-mlx/dflash-mlx implements exact speculative decoding for language models on Apple Silicon using Metal and MLX, reducing forward passes with a block-diffusion draft model and per-layer KV cache rollback.https://ramdi.fr/github-stars/gemma-gem-running-large-language-models-in-chrome-with-webgpu-acceleration/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/gemma-gem-running-large-language-models-in-chrome-with-webgpu-acceleration/Gemma-gem is a TypeScript Chrome extension using WebGPU to run large language models like E2B and E4B directly in the browser. It requires a recent Chrome and offers GPU-accelerated inference.https://ramdi.fr/github-stars/hands-on-large-language-models-a-practical-visual-journey-through-llm-engineering/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/hands-on-large-language-models-a-practical-visual-journey-through-llm-engineering/Explore the Hands-On Large Language Models repo, a Jupyter notebook-based practical guide from fundamentals to fine-tuning, designed for hands-on LLM learning on free Colab GPUs.https://ramdi.fr/github-stars/inside-alibaba-s-logics-parsing-v2-end-to-end-structured-document-parsing-beyond-ocr/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/inside-alibaba-s-logics-parsing-v2-end-to-end-structured-document-parsing-beyond-ocr/Alibaba’s Logics-Parsing-v2 converts complex document images into structured HTML, handling formulas, tables, flowcharts, music sheets, and pseudocode with a single model.https://ramdi.fr/github-stars/inside-genie-envisioner-a-two-stage-video-diffusion-platform-for-robotic-manipulation/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/inside-genie-envisioner-a-two-stage-video-diffusion-platform-for-robotic-manipulation/Genie Envisioner offers a two-stage training pipeline using video diffusion for robotic manipulation, separating world model adaptation from action policy learning. Here’s how it works and how to get started.https://ramdi.fr/github-stars/inside-nousresearch-s-finetuning-subnet-continuous-incentivized-fine-tuning-for-llms-on-bittensor/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/inside-nousresearch-s-finetuning-subnet-continuous-incentivized-fine-tuning-for-llms-on-bittensor/NousResearch’s finetuning-subnet enables continuous, incentivized fine-tuning of LLMs using synthetic data from a separate subnet, pioneering cross-subnet communication in Bittensor.https://ramdi.fr/github-stars/magi-a-structured-multi-llm-debate-system-with-iterative-critique-and-voting/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/magi-a-structured-multi-llm-debate-system-with-iterative-critique-and-voting/MAGI implements a multi-round debate protocol among three LLMs to match stronger models’ accuracy via iterative critique and voting. It offers fault tolerance, adaptive escalation, and persona presets.https://ramdi.fr/github-stars/magika-google-s-deep-learning-system-for-fast-accurate-file-type-detection/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/magika-google-s-deep-learning-system-for-fast-accurate-file-type-detection/Magika replaces magic-byte heuristics with a tiny deep learning model for file type detection, achieving ~99% accuracy across 200+ types with 5ms CPU inference.https://ramdi.fr/github-stars/mapping-the-open-source-ai-stack-with-the-awesome-opensource-ai-curated-list/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/mapping-the-open-source-ai-stack-with-the-awesome-opensource-ai-curated-list/A curated directory cataloging over 200 production-ready open-source AI projects across the machine learning stack, from training frameworks to self-hosted UIs.https://ramdi.fr/github-stars/microgpt-c-coordinating-tiny-gpt-2-models-in-c-for-edge-logical-reasoning/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/microgpt-c-coordinating-tiny-gpt-2-models-in-c-for-edge-logical-reasoning/MicroGPT-C uses a deterministic C scaffold to coordinate tiny GPT-2 models, achieving 90%+ accuracy on logic games with 8x memory compression and infinite sequence lengths.https://ramdi.fr/github-stars/multiworld-a-unified-framework-for-multi-agent-multi-view-video-world-modeling/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/multiworld-a-unified-framework-for-multi-agent-multi-view-video-world-modeling/MultiWorld offers a unified framework for multi-agent multi-view video world modeling using a frozen VGGT backbone for implicit 3D understanding. It supports scalable multi-agent control and autoregressive inference.https://ramdi.fr/github-stars/navigating-the-mlops-maze-a-deep-dive-into-the-awesome-production-machine-learning-repository/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/navigating-the-mlops-maze-a-deep-dive-into-the-awesome-production-machine-learning-repository/Explore the EthicalML awesome-production-machine-learning repo, a curated catalog of 200+ open source MLOps tools covering the full production ML lifecycle. Essential for ML engineers building production stacks.https://ramdi.fr/github-stars/omni-diffusion-unified-any-to-any-multimodal-generation-with-masked-discrete-diffusion/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/omni-diffusion-unified-any-to-any-multimodal-generation-with-masked-discrete-diffusion/Omni-Diffusion models text, image, and speech tokens jointly via masked discrete diffusion, enabling any-to-any multimodal generation with a single unified model.https://ramdi.fr/github-stars/onnxmltools-a-python-toolkit-for-converting-ml-models-to-onnx-format/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/onnxmltools-a-python-toolkit-for-converting-ml-models-to-onnx-format/onnxmltools is a Python library for converting machine learning models from various frameworks into the ONNX format, enabling interoperability across runtimes and platforms.https://ramdi.fr/github-stars/opengame-generating-playable-web-games-from-natural-language-with-a-dual-skill-llm-framework/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/opengame-generating-playable-web-games-from-natural-language-with-a-dual-skill-llm-framework/OpenGame from CUHK MMLab generates full web games from natural language prompts using a dual-skill LLM architecture that maintains cross-file consistency and integration fixes.https://ramdi.fr/github-stars/orion-direct-access-to-apple-neural-engine-for-on-device-llm-training/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/orion-direct-access-to-apple-neural-engine-for-on-device-llm-training/Orion bypasses CoreML to access Apple’s Neural Engine directly via private frameworks, enabling on-device inference and fine-tuning of small LLMs with 8.5x reduced training overhead.https://ramdi.fr/github-stars/paper2code-auditing-ambiguity-in-ml-paper-code-generation-with-citation-anchored-implementations/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/paper2code-auditing-ambiguity-in-ml-paper-code-generation-with-citation-anchored-implementations/paper2code transforms arxiv papers into Python code with ambiguity auditing and inline citations, prioritizing traceability over completeness in ML implementations.https://ramdi.fr/github-stars/simscale-a-scalable-sim-real-co-training-pipeline-for-autonomous-driving-planners/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/simscale-a-scalable-sim-real-co-training-pipeline-for-autonomous-driving-planners/SimScale provides a sim-real co-training pipeline for autonomous driving planners, combining synthetic simulation data with real-world data to improve robustness and generalization across multiple planner types.https://ramdi.fr/github-stars/tribev2-pretrained-models-for-predicting-brain-responses-to-videos/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/tribev2-pretrained-models-for-predicting-brain-responses-to-videos/tribev2 offers pretrained models to predict brain responses to videos using cortical mesh modeling. Supports video, text, and audio inputs with easy inference setup.https://ramdi.fr/github-stars/understanding-llm-internals-a-hands-on-guide-to-transformers-and-attention-math/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/understanding-llm-internals-a-hands-on-guide-to-transformers-and-attention-math/A curated repo breaking down large language model internals with numeric attention math, tokenization, and transformer architecture, targeting engineers who want to understand LLMs under the hood.https://ramdi.fr/github-stars/vllm-mlx-efficient-llm-serving-on-apple-silicon-with-ssd-tiered-kv-cache-and-continuous-batching/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/vllm-mlx-efficient-llm-serving-on-apple-silicon-with-ssd-tiered-kv-cache-and-continuous-batching/vllm-mlx is a Python inference server for Apple Silicon that supports OpenAI and Anthropic APIs, featuring SSD-tiered KV cache for long-context agents and continuous batching for performance.https://ramdi.fr/github-stars/a-practical-taxonomy-for-large-language-model-ensembles-exploring-the-awesome-llm-ensemble-repository/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/a-practical-taxonomy-for-large-language-model-ensembles-exploring-the-awesome-llm-ensemble-repository/The Awesome-LLM-Ensemble repo catalogs research on combining multiple LLMs with a clear three-phase taxonomy: before, during, and after inference ensemble methods.https://ramdi.fr/github-stars/a-ranked-directory-of-atomistic-machine-learning-projects-with-a-composite-quality-score/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/a-ranked-directory-of-atomistic-machine-learning-projects-with-a-composite-quality-score/Explore a curated, ranked list of 510 open-source atomistic machine learning projects scored by combined GitHub and package manager metrics — a model for scientific computing ecosystems.https://ramdi.fr/github-stars/avatar-forcing-real-time-multimodal-head-avatar-generation-with-diffusion-forcing/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/avatar-forcing-real-time-multimodal-head-avatar-generation-with-diffusion-forcing/Avatar Forcing implements diffusion forcing for causal, real-time multimodal input processing enabling expressive head avatars with ~500ms latency and 6.8X speedup over baselines.https://ramdi.fr/github-stars/curating-quality-a-curated-list-of-essential-books-for-large-language-model-engineers/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/curating-quality-a-curated-list-of-essential-books-for-large-language-model-engineers/A curated list of 24 rigorously selected books on LLM engineering, covering foundational theory to production deployment. Highlights a unique 6-step quality filtering process.https://ramdi.fr/github-stars/exploring-deepmind-s-representations4d-advanced-self-supervised-video-representations-with-moving-latent-tokens/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/exploring-deepmind-s-representations4d-advanced-self-supervised-video-representations-with-moving-latent-tokens/Google DeepMind’s representations4d bundles three self-supervised video learning approaches using transformers, including a novel object-centric tracking method with latent tokens moving off the pixel grid.https://ramdi.fr/github-stars/forensix-ml-powered-forensic-analysis-of-chrome-and-brave-browser-artifacts/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/forensix-ml-powered-forensic-analysis-of-chrome-and-brave-browser-artifacts/ForensiX combines ML-driven URL classification with browser artifact extraction for forensic analysis of Chrome and Brave data. Docker-based deployment included.https://ramdi.fr/github-stars/inside-llm-madness-a-lightweight-gpt-transformer-training-pipeline-with-built-in-visualization/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/inside-llm-madness-a-lightweight-gpt-transformer-training-pipeline-with-built-in-visualization/llm-madness offers a Python-built GPT-style transformer training pipeline with tokenizer training, memory-mapped datasets, and a unique web UI for per-layer attention inspection and loss visualization.https://ramdi.fr/github-stars/inside-ltx-video-generator-for-mac-bridging-swiftui-with-python-for-local-ai-video-generation/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/inside-ltx-video-generator-for-mac-bridging-swiftui-with-python-for-local-ai-video-generation/LTX Video Generator for Mac runs complex AI video generation entirely on Apple Silicon by bridging native SwiftUI with a Python subprocess. It manages large models, audio-video sync, and long tasks locally.https://ramdi.fr/github-stars/megatrain-ram-centric-training-architecture-for-100b-parameter-llms-on-a-single-gpu/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/megatrain-ram-centric-training-architecture-for-100b-parameter-llms-on-a-single-gpu/MegaTrain enables training 100B+ parameter LLMs on a single GPU by offloading all parameters to CPU RAM and streaming layers to GPU. Supports HuggingFace models and multi-GPU data parallelism without NCCL.https://ramdi.fr/github-stars/nas3r-self-supervised-3d-reconstruction-and-camera-pose-estimation-with-gaussian-splatting/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/nas3r-self-supervised-3d-reconstruction-and-camera-pose-estimation-with-gaussian-splatting/NAS3R enables self-supervised 3D geometry and camera parameter estimation without ground-truth data, using Gaussian splatting and a VGGT backbone. It supports multi-view setups and optional pretrained initialization.https://ramdi.fr/github-stars/omnistream-a-multi-frame-transformer-for-continuous-video-stream-perception/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/omnistream-a-multi-frame-transformer-for-continuous-video-stream-perception/OmniStream uses a multi-frame transformer to process continuous video streams with patch-level temporal indexing, supporting downstream vision-language-action tasks.https://ramdi.fr/github-stars/openmythos-exploring-recurrent-depth-transformers-with-input-injection-for-sustained-reasoning/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/openmythos-exploring-recurrent-depth-transformers-with-input-injection-for-sustained-reasoning/OpenMythos implements a recurrent-depth transformer that recycles layers via looped blocks, using input injection to prevent signal drift. It scales from 1B to 1T parameters with up to 1M token context.https://ramdi.fr/github-stars/simrecon-compositional-3d-scene-reconstruction-with-viewpoint-optimization-and-semantic-graph-synthesis/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/simrecon-compositional-3d-scene-reconstruction-with-viewpoint-optimization-and-semantic-graph-synthesis/SimRecon converts real-world videos into simulation-ready 3D scenes by combining geometry reconstruction, instance segmentation, viewpoint optimization, and semantic scene graph synthesis.https://ramdi.fr/github-stars/voice-clone-studio-unified-modular-web-ui-for-multi-engine-voice-cloning-and-tts/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/voice-clone-studio-unified-modular-web-ui-for-multi-engine-voice-cloning-and-tts/Voice Clone Studio unifies multiple voice AI engines in a modular Gradio web UI. Supports voice cloning, multi-speaker dialogs, speech-to-speech, and LoRA fine-tuning with GPU or Apple Silicon.https://ramdi.fr/github-stars/agenticailabs-ai-engineering-roadmap-a-modular-curriculum-for-self-taught-ai-engineers/Mon, 04 May 2026 10:08:13 +0000https://ramdi.fr/github-stars/agenticailabs-ai-engineering-roadmap-a-modular-curriculum-for-self-taught-ai-engineers/AgenticAiLabs AI Engineering Roadmap offers a modular, community-curated curriculum for self-taught AI engineers, covering from fundamentals to advanced AI topics like LLMs and RAG.https://ramdi.fr/github-stars/building-a-production-ready-second-brain-with-agentic-rag-and-llmops/Sun, 03 May 2026 08:12:11 +0000https://ramdi.fr/github-stars/building-a-production-ready-second-brain-with-agentic-rag-and-llmops/Explore an open-source course that teaches building a production-grade AI assistant using advanced retrieval-augmented generation, agent orchestration, fine-tuning, and LLMOps practices.https://ramdi.fr/github-stars/a-hands-on-course-for-mastering-large-language-models-fine-tuning-quantization-and-tooling/Sat, 02 May 2026 20:07:04 +0000https://ramdi.fr/github-stars/a-hands-on-course-for-mastering-large-language-models-fine-tuning-quantization-and-tooling/Explore a comprehensive LLM course with practical notebooks on fine-tuning (QLoRA, DPO), quantization (GPTQ), and tools like AutoEval and LazyMergekit. Ideal for aspiring LLM engineers.https://ramdi.fr/github-stars/annotated-deep-learning-paper-implementations-annotated-pytorch-implementations-of-key-deep-learning-papers/Sat, 02 May 2026 20:07:04 +0000https://ramdi.fr/github-stars/annotated-deep-learning-paper-implementations-annotated-pytorch-implementations-of-key-deep-learning-papers/This repo provides annotated PyTorch implementations of major deep learning papers with side-by-side explanations, aiding understanding and prototyping.https://ramdi.fr/github-stars/exploring-microsoft-s-generative-ai-for-beginners-a-dual-language-practical-course/Sat, 02 May 2026 20:07:04 +0000https://ramdi.fr/github-stars/exploring-microsoft-s-generative-ai-for-beginners-a-dual-language-practical-course/Microsoft’s “Generative AI for Beginners” offers 21 lessons with Python and TypeScript examples covering LLMs, prompt engineering, RAG, and AI app building.https://ramdi.fr/github-stars/llamafactory-modular-extensible-fine-tuning-framework-for-large-language-models/Sat, 02 May 2026 20:07:04 +0000https://ramdi.fr/github-stars/llamafactory-modular-extensible-fine-tuning-framework-for-large-language-models/LlamaFactory offers a modular Python framework for fine-tuning 100+ LLMs with diverse algorithms and optimizations, including LoRA, QLoRA, and reinforcement learning.https://ramdi.fr/github-stars/microsoft-s-ml-for-beginners-a-project-based-classic-machine-learning-curriculum/Sat, 02 May 2026 20:07:04 +0000https://ramdi.fr/github-stars/microsoft-s-ml-for-beginners-a-project-based-classic-machine-learning-curriculum/Microsoft’s ML-For-Beginners offers a 12-week, project-based classic machine learning course using Scikit-learn and Jupyter Notebooks, focusing on foundational concepts with interactive lessons and quizzes.https://ramdi.fr/github-stars/symfony-ai-unified-ai-integration-for-php-applications-with-symfony/Sat, 02 May 2026 20:07:04 +0000https://ramdi.fr/github-stars/symfony-ai-unified-ai-integration-for-php-applications-with-symfony/Symfony AI unifies multiple AI platforms into a single PHP interface, enabling flexible AI-powered Symfony apps without vendor lock-in. It includes AI agents, chat context, and data indexing components.https://ramdi.fr/github-stars/vllm-efficient-large-language-model-serving-with-paged-attention-and-continuous-batching/Sat, 02 May 2026 20:07:04 +0000https://ramdi.fr/github-stars/vllm-efficient-large-language-model-serving-with-paged-attention-and-continuous-batching/vLLM is a Python library for high-throughput LLM inference using paged attention and continuous batching. It supports quantization, distributed inference, and an OpenAI-compatible API.https://ramdi.fr/github-stars/comfyui-modular-visual-workflows-for-diffusion-model-experimentation/Sun, 26 Apr 2026 17:51:11 +0000https://ramdi.fr/github-stars/comfyui-modular-visual-workflows-for-diffusion-model-experimentation/ComfyUI offers a graph/node interface for building complex diffusion model workflows offline, blending modularity with flexibility for AI practitioners.https://ramdi.fr/github-stars/dive-into-deep-learning-d2l-ai-chinese-edition-an-interactive-textbook-bridging-theory-and-code/Sun, 26 Apr 2026 17:51:11 +0000https://ramdi.fr/github-stars/dive-into-deep-learning-d2l-ai-chinese-edition-an-interactive-textbook-bridging-theory-and-code/Dive into Deep Learning Chinese edition offers an interactive, code-driven deep learning textbook in Python, integrating theory with runnable examples for hands-on learning.https://ramdi.fr/github-stars/pytorch-s-dynamic-neural-networks-and-tape-based-autograd-a-deep-dive-into-flexible-deep-learning/Sun, 26 Apr 2026 17:51:11 +0000https://ramdi.fr/github-stars/pytorch-s-dynamic-neural-networks-and-tape-based-autograd-a-deep-dive-into-flexible-deep-learning/Explore PyTorch’s unique tape-based autograd and dynamic neural networks architecture that enables flexible model development and efficient GPU-accelerated tensor computation.https://ramdi.fr/github-stars/tensorflow-a-versatile-platform-powering-machine-learning-from-research-to-production/Sun, 26 Apr 2026 17:51:11 +0000https://ramdi.fr/github-stars/tensorflow-a-versatile-platform-powering-machine-learning-from-research-to-production/TensorFlow is a comprehensive open-source machine learning platform with stable multi-language APIs and broad hardware support, evolving from research prototype to production-ready ecosystem.https://ramdi.fr/github-stars/hugging-face-transformers-a-unified-api-for-state-of-the-art-ai-models-across-modalities/Sun, 26 Apr 2026 09:31:26 +0000https://ramdi.fr/github-stars/hugging-face-transformers-a-unified-api-for-state-of-the-art-ai-models-across-modalities/Hugging Face Transformers offers a unified Python API to access over 1 million pretrained AI models for text, vision, and audio, simplifying complex pipelines with its Pipeline API.https://ramdi.fr/github-stars/inside-tesseract-ocr-from-legacy-character-recognition-to-lstm-based-line-recognition/Sun, 26 Apr 2026 09:31:26 +0000https://ramdi.fr/github-stars/inside-tesseract-ocr-from-legacy-character-recognition-to-lstm-based-line-recognition/Tesseract OCR evolved from a legacy character pattern engine to a modern LSTM-based line recognition system supporting 100+ languages and multiple output formats. Here’s a technical dive.https://ramdi.fr/github-stars/keras-3-multi-backend-deep-learning-framework-simplifying-model-development-across-jax-tensorflow-and-pytorch/Sun, 26 Apr 2026 09:31:26 +0000https://ramdi.fr/github-stars/keras-3-multi-backend-deep-learning-framework-simplifying-model-development-across-jax-tensorflow-and-pytorch/Keras 3 introduces a multi-backend architecture supporting JAX, TensorFlow, PyTorch, and OpenVINO, enabling flexible, accelerated deep learning model development with up to 350% speedups.https://ramdi.fr/github-stars/netdata-real-time-edge-monitoring-with-integrated-machine-learning-anomaly-detection/Sun, 26 Apr 2026 09:31:26 +0000https://ramdi.fr/github-stars/netdata-real-time-edge-monitoring-with-integrated-machine-learning-anomaly-detection/Netdata delivers per-second real-time monitoring with minimal overhead. Its edge-based ML-powered anomaly detection and scalable distributed design make it a solid choice for diverse infrastructures.https://ramdi.fr/github-stars/mlflow-unified-ai-engineering-for-llms-and-traditional-machine-learning/Fri, 24 Apr 2026 18:26:13 +0000https://ramdi.fr/github-stars/mlflow-unified-ai-engineering-for-llms-and-traditional-machine-learning/MLflow offers a unified open-source platform managing lifecycle and observability for both LLM-based AI agents and traditional ML models, with vendor neutrality and production-grade features.