Library

Search the public knowledge base.

Machine Learning Reinforcement Learning Transformers LLMs Attention Diffusion 3D hand pose estimation AI infrastructure AI Interpretability AI security

45 results

Sort by

Latest Most read Recently updated

Next gen

World Models: From Why Agents Dream to DreamerV3

An interactive series you work through: predict, play, derive and break things, from Dyna to every trick inside DreamerV3, ending with a world model you drive in your browser.

Library

World Models: From Why Agents Dream to DreamerV3

HaWoR: Putting Egocentric Hands Back in the World

MCP Explained: How AI Connects to the Tools and Data You Use

Tokenization for LLMs: From Raw Text to Model Inputs

Mechanistic Interpretability: Reverse-Engineering the Algorithms Inside Neural Networks

World Models: Learning Enough of the Future to Act

veScale-FSDP: Flexible, Structure-Aware Sharding at 10K-GPU Scale

DeepSeek's Plugin Paradigm: Spatiotemporal Composability

Beyond Reinforcement Learning: Sampling as Optimization for Reasoning Models

WarpSAC: When More Data Changes the Right RL Algorithm

Attention Is All You Need: The Transformer

Action Chunking with Transformers (ACT): Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware

B-spline Policy: Continuous Action Curves for Fast Manipulation

DemoSpeedup: Entropy-Guided Acceleration of Visuomotor Policy Learning

Backend Engineering from First Principles

From Imitation to Refinement – Residual RL for Precise Robotic Assembly

HIL-SERL: Human-in-the-Loop Sample-Efficient Robotic Reinforcement Learning for Dexterous Manipulation

Imitation Bootstrapped Reinforcement Learning (IBRL)

AI Guardrails and Safety: From Failure Modes to Enforcement

Machine-Checkable Termination Guarantees for Bayesian Trust in Multi-Agent Systems

Harness Engineering: Building Reliable Evaluation and Data Pipelines for ML Systems

Dive into Claude Code: Design Space of Today’s and Future AI Agent Systems

Imitation Bootstrapped Reinforcement Learning (IBRL): Using Demonstrations in Exploration and Bootstrapping

KV Caching in Autoregressive Transformers

Speculative Decoding: Lossless Acceleration for Large Language Models

World Action Models are Zero-shot Policies: The DreamZero Approach

Odysseus: Stable RL Training of VLMs for Long-Horizon Game Decision-Making

ECHO: Turning Terminal Feedback into Dense Supervision for Agent RL

Mastering the Game of Go with Deep Neural Networks and Tree Search

Vision-Language-Action Models: From Pixels and Instructions to Robot Actions

DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models

Maximum Likelihood Reinforcement Learning (MaxRL): A Compute-Indexed Bridge from RL to Log-Likelihood

Reinforcement Learning for Large Language Models: Group Relative Policy Optimization (GRPO)

Kubernetes Architecture and Networking in Depth

LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architectures from Pixels

Recursive Language Models: Scaling LLM Contexts via Symbolic Recursion

Vector Embeddings and Vector Databases

Mamba-3: Improved Sequence Modeling using State Space Principles

World Models: Learning to Dream for Efficient Reinforcement Learning

I-JEPA: Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture

Transformers: Attention, Architecture, Training, and Scaling

Diffusion Models and Flow Matching: From Score-Based Diffusion to Continuous Normalizing Flows

LoRA Fine-Tuning: Low-Rank Adaptation of Large Neural Networks

Variational Autoencoders: Principles, Derivations, and Applications

Policy Gradient Methods