AI Bookmarks
Last updated: 2026-04-03 19:57 | 281 links | 40 categories
Categories
RL (4)
[back to top]
papers (132)
- 2408.12528
- 2404.02905
- LLaVA
- 2111.14822
- All Are Worth Words: A ViT Backbone for Diffusion Models
- AI Academic Reader | Paper Digest
- 2408.11039
- Multiple object tracking: A literature review - ScienceDirect
- AudioLDM: Text-to-Audio Generation with Latent Diffusion Models
- Large Language Diffusion Models
- 2407.15595
- [2406.07524] Simple and Effective Masked Diffusion Language Models
- 2210.02747
- language_understanding_paper.pdf
- 2505.15778
- 2304.08485
- 491108998_1064335232204123_244838803708223849_n.pdf
- Deepseek Papers - a Presidentlin Collection
- 2505.12540
- arxiv.org/pdf/2505.00675
- 1. Introduction — CUDA C++ Programming Guide
- 2505.19590
- 2405.00334
- 2402.01364
- 2505.21444
- [2505.22954] Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents
- HCPLab-SYSU/Embodied_AI_Paper_List: [Embodied-AI-Survey-2025] Paper List and Resource Repository for Embodied AI
- Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI
- haoranD/Awesome-Embodied-AI: A curated list of awesome papers on Embodied AI and related research/industry-driven resources.
- [2402.02385] A Survey on Robotics with Foundation Models: toward Embodied AI
- @Kseniase on Hugging Face: "12 Foundational AI Model Types Let’s refresh some fundamentals today to stay…"
- 1410.5401
- cudabook.pdf
- GT-RIPL/Awesome-LLM-Robotics: A comprehensive list of papers using large language/multi-modal models for Robotics/RL, including papers, codes, and related websites
- Large Language Models for Robotics: A Survey
- NetMirror APP - Watch Movies and Series
- 2306.14846
- Embodied AI Agents: Modeling the World
- 2406.09246
- 2310.08864
- 2301.08243
- CS294/194-280 Advanced Large Language Model Agents | CS 294/194-280 Advanced Large Language Model Agents
- Jeremy Jordan
- Transformers from scratch | peterbloem.nl
- GitHub - analyticalrohit/AI-ML-Cheatsheets: All standford Cheatsheets: Artificial Intelligence, Transformers, LLMs, Deep Learning, Machine Learning, Probabilities, Statistics, Algebra and Calculus.
- GitHub - google-gemini/genai-processors: GenAI Processors is a lightweight Python library that enables efficient, parallel content processing.
- 2507.10524v1.pdf
- Kimi-K2/tech_report.pdf at main · MoonshotAI/Kimi-K2 · GitHub
- [Full Workshop] Reinforcement Learning, Kernels, Reasoning, Quantization & Agents — Daniel Han - YouTube
- 2507.15028v1.pdf
- Instagram
- 2407.18384v3.pdf
- MatchGuard - Firebase Studio
- 2507.18074v1.pdf
- 2003.02436
- GitHub - Engineer1999/A-Curated-List-of-ML-System-Design-Case-Studies: This repository contains a curated collection of 300 case studies from over 80 companies, detailing practical applications and insights into machine learning (ML) system design. The contents are organized to help you easily find relevant case studies based on industry or specific ML use cases.
- CS294/194-196 Large Language Model Agents | CS 194/294-196 Large Language Model Agents
- (3) CS 194/294-280 (Advanced LLM Agents) - Lecture 12, Dawn Song - YouTube
- Super Sale – Harmonshirt.in
- PyTorch in One Hour: From Tensors to Training Neural Networks on Multiple GPUs
- 2506.21734v2.pdf
- 2507.21046v2.pdf
- Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving | alphaXiv
- arxiv.org/pdf/2507.21206
- fchollet/deep-learning-with-python-notebooks: Jupyter notebooks for the code samples of the book "Deep Learning with Python"
- 2501.09223v2.pdf
- 2507.22229v1.pdf
- Fall 2025 Reading List (##201-210) – Aleksey Charapko
- avatarl: training language models from scratch with pure reinforcement learning - tokenbender
- Generative modelling in latent space – Sander Dieleman
- [2508.09874] Memory Decoder: A Pretrained, Plug-and-Play Memory for Large Language Models
- From Scratch | Michal Pitr | Substack
- Building a web search engine from scratch in two months with 3 billion neural embeddings
- Loading PDF…
- GitHub - clu0/unet.cu: UNet diffusion model in pure CUDA
- How To Scale Your Model
- [2508.16204] Competition and Attraction Improve Model Fusion
- New Tab
- 2508.15884v1.pdf
- 27 - The Year Everything Changes - by BOSS | Beauty Of SaaS
- How To Become A Mechanistic Interpretability Researcher — AI Alignment Forum
- How to Build a Complete End-to-End NLP Pipeline with Gensim: Topic Modeling, Word Embeddings, Semantic Search, and Advanced Text Analysis - MarkTechPost
- Dive into Deep Learning — Dive into Deep Learning 1.0.3 documentation
- fchollet (fchollet) / Repositories
- How Attention Sinks Keep Language Models Stable
- manji mali book - Google Search
- [2509.04475] ParaThinker: Native Parallel Thinking as a New Paradigm to Scale LLM Test-time Compute
- 1904.10509v1.pdf
- Hierarchical Reasoning Model assembly manual for toddlers
- Deep Learning with Yacine | Yacine Mahdid | Substack
- Parallel-R1: Towards Parallel Thinking via Reinforcement Learning
- 2504.15228v2.pdf
- (2) AI Career Advice From a Top 1% Engineer (feat. Jean Lee!) - YouTube
- Defeating Nondeterminism in LLM Inference - Thinking Machines Lab
- id2223kth.github.io/assignments/2025/ID2223Projects2025.html
- 2403.18103v3.pdf
- 2509.08827v1.pdf
- SpikingBrain Technical Report: Spiking Brain-inspired Large Models
- Qwen
- Why language models hallucinate | OpenAI
- Paged Attention from First Principles: A View Inside vLLM | Hamza's Blog
- Flow Matching in 5 Minutes | wh
- The Darwin Gödel Machine: AI that improves itself by rewriting its own code
- GitHub - google-agentic-commerce/AP2: Building a Secure and Interoperable Future for AI-Driven Payments.
- ATLAS: Learning to Optimally Memorize the Context at Test Time
- DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning
- All Posts – Sander Dieleman
- Chapters - Deep Learning with Python
- Making Deep Learning go Brrrr From First Principles
- Transformer Inference Arithmetic | kipply's blog
- Domain specific architectures for AI inference
- Post-training 101 | Tokens for Thoughts
- The Illustrated Transformer – Jay Alammar – Visualizing machine learning one concept at a time.
- TPU Deep Dive
- Understanding Deep Learning
- Stanford CS329A | Self-Improving AI Agents
- Agentic Design Patterns - Google Docs
- ai-agents-for-beginners/13-agent-memory at main · microsoft/ai-agents-for-beginners
- Learning Deep Representations of Data Distributions
- book-main.pdf
- 2510.04871v1.pdf
- LeetGPU - The GPU Programming Platform
- Agent Learning via Early Experience
- 2510.17558v1.pdf
- Dummy's Guide to Modern Samplers
- 2510.21890v1.pdf
- 10-703 Deep RL
- 10-703 Deep RL | Schedule
- Evaluation in information retrieval
- Introduction to Information Retrieval
- The Smol Training Playbook: The Secrets to Building World-Class LLMs
- How I Got a Job at Google DeepMind (No ML Degree) | Medium
[back to top]
Robots (2)
[back to top]
Agents & MCP (4)
[back to top]
Blogs & People (4)
[back to top]
Books & PDFs (2)
[back to top]
Diffusion Models (1)
[back to top]
GPU & CUDA (5)
[back to top]
MLOps & Deployment (2)
[back to top]
Memory & Context (1)
[back to top]
RL & Alignment (2)
[back to top]
Research Papers (3)
[back to top]
[back to top]
interview (6)
[back to top]
Uncategorized
- ML Books - Google Drive
- The Ultimate Guide to Fine-Tuning LLMs from Basics to Breakthroughs: An Exhaustive Review of Technologies, Research, Best Practices, Applied Research Challenges and Opportunities (Version 1.0)
- kuleshov-group/awesome-discrete-diffusion-models: A curated list for awesome discrete diffusion models resources.
- mlabonne/llm-course: Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
- Machine Learning Design Interview: Machine Learning System Design Interview
- AI Engineering
- (2) Build an LLM from Scratch 1: Set up your code environment - YouTube
- Uygar Kurt - YouTube
- GitHub - langchain-ai/agents-from-scratch
- aie-book/resources.md at main · chiphuyen/aie-book · GitHub
- d2l-en.pdf
- ML Resources
- Build MLOps Fine-Tune System on GCP From Scratch
- Build Your Own ViT Model from Scratch
- Petals – Run LLMs at home, BitTorrent-style
- turbopuffer
- 1y33/100Days: GPU Kernels
- 1y33.github.io/projects/
- a-hamdi/GPU: 100 days of building GPU kernels!
- 100-days-of-gpu/CUDA.md at main · hkproj/100-days-of-gpu
- Quickstart — JAX documentation
- Zero to Mastery Learn PyTorch for Deep Learning
- tech-books-library/AI & Machine Learning (Deep Learning, NLP, etc.)/Natural Language Processing with PyTorch - Build Intelligent Language Applications Using Deep Learning.pdf at master · HarshVadaliya/tech-books-library · GitHub
- Learning PyTorch with Examples — PyTorch Tutorials 2.7.0+cu126 documentation
- Reinforcement Learning of Large Language Models - YouTube
- Architectural Decision Records (ADRs) | Architectural Decision Records
- Refactoring and Design Patterns
- microsoft/ai-agents-for-beginners: 12 Lessons to Get Started Building AI Agents
- Blog - Aleksa Gordić
- Deep-ML
- Smth Smth GPU Related
- 🔥 Introduction - Mojo 🔥 GPU Puzzles
- Blog | Modal
- Hello, world! | Modal Docs
- LeetGPU - The GPU Programming Platform
- PyTorch internals : ezyang’s blog
- README | GPU Glossary
- Fabien Sanglard's Website
- What is a GPU Core? | GPU Glossary
- What Every Programmer Should Know About Memory
- AI/ML Roadmap for beginner To Advanced - sigmoidit.com
- 2006.11239
- Deep+Learning+Ian+Goodfellow.pdf
- Practical Deep Learning for Coders - 25: Latent diffusion
- Inside NVIDIA GPUs: Anatomy of high performance matmul kernels - Aleksa Gordić
- Blog | kalomaze's kalomazing blog
- Robot Learning: A Tutorial - a Hugging Face Space by lerobot
- A case for learning GPU programming with a compute-first mindset – Maister's Graphics Adventures
- Spaces - Hugging Face
- We’re open-sourcing our text-to-image model and the process behind it
- 1.1. Introduction — CUDA Programming Guide
- AI Maestro - Orchestrate Your AI Coding Agents
- We Got Claude to Fine-Tune an Open Source LLM
- How prompt caching works - Paged Attention and Automatic Prefix Caching plus practical tips | sankalp's blog
- kipply's blog
- stas00/ml-engineering: Machine Learning Engineering Open Book
- vllm-project/vllm: A high-throughput and memory-efficient inference and serving engine for LLMs
- GitHub - harvard-edge/cs249r_book: Introduction to Machine Learning Systems
- Deep-ML | Practice Problems
- PayPal-R/Infra-AI: slack integration with MCP servers
- How we built our multi-agent research system \ Anthropic
- 3.1. Advanced CUDA APIs and Features — CUDA Programming Guide
- Tensor Parallelism (TP) in Transformers: 5 Minutes to Understand
- The ML Trench
- Spotyy – Remote Config – Parameters – Firebase console
- andri27-ts/Reinforcement-Learning: Learn Deep Reinforcement Learning in 60 days! Lectures & Code in Python. Reinforcement Learning + Deep Learning
- Notion
- The Roadmap of Mathematics for Machine Learning
- GitHub - ritchieng/the-incredible-pytorch: The Incredible PyTorch: a curated list of tutorials, papers, projects, communities and more relating to PyTorch.
- GitHub - aishwaryanr/awesome-generative-ai-guide: A one stop repository for generative AI research updates, interview resources, notebooks and much more!
- Uplers | Opportunity
- GitHub - GokuMohandas/Made-With-ML: Learn how to design, develop, deploy and iterate on production-grade ML applications.
- moltbook - the front page of the agent internet
- GitHub - HamzaElshafie/gpt-oss-20B: A PyTorch implementation of the GPT-OSS-20B architecture. All components are coded from scratch: RoPE with YaRN, RMSNorm, SwiGLU with clamping and residual connection, Mixture-of-Experts (MoE), Self-Attention with learned sinks, banded attention, GQA, and KV-cache.
- CMU LTI Summer 2026 Internship Program Application
- GitHub - modal-projects/modal-jazz: we have ai at home
- microgpt · GitHub
- PacktPublishing/Agentic-Architectural-Patterns-for-Building-Multi-Agent-Systems: Agentic Architectural Patterns for Building Multi-Agent Systems, published by Packt
- HydraDB - serverless context infra for AI
- Saurabh's Website
- GitHub - liquidslr/interview-company-wise-problems: Lists of company wise questions. Every csv file in the companies directory corresponds to a list of questions on leetcode for a specific company based on the leetcode company tags. Updated as of 20 June, 2025 · GitHub
- State of RL for reasoning LLMs | A. Weers
- Efficient Memory Management for Large Language Model Serving with PagedAttention
- Suvash Sedhain | Blog
- A Visual Guide to Quantization - by Maarten Grootendorst
- Blog and Notes | Sebastian Raschka, PhD
- Lil'Log
- blog | Ziming Liu
- Lil'Log
- A Visual Guide to Attention Variants in Modern LLMs
- World Models
- GuochenZhou/World-Model: A paper list of world model
- World Models
- Simon Willison’s Weblog
- arxiv.org/pdf/2506.22355?
- accelerated-computing-hub/tutorials/accelerated-python/notebooks/syllabi/cuda_python__cupy_cudf_cccl_kernels__8_hours.ipynb at main · NVIDIA/accelerated-computing-hub · GitHub
- Achieve 23x LLM Inference Throughput & Reduce p50 Latency
- Welcome to Ray! — Ray 2.54.1
- Optimization story: Bloom inference
- ray-project/llm-numbers: Numbers every LLM developer should know
- [2402.17764] The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
- [2310.11453] BitNet: Scaling 1-bit Transformers for Large Language Models
- 2402.17764
- Internet Security by Zscaler
- Advancing AI for Humanity
- Advancing AI for Humanity
- Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet
- Transformer Circuits Thread
- Activation Atlas
- Distill — Latest articles about machine learning
- A Comprehensive Mechanistic Interpretability Explainer & Glossary - Dynalist
281 links across 14 categories
source