FeynmanWiki
ExploreLibraryRoadmapsCreateMy blogsPricing

Library

Search the public knowledge base.

Filters

Reset all

Categories

Machine Learning22Reinforcement Learning11Transformers5LLMs4Attention3Diffusion2AI Interpretability1BPE1causal interventions1context paradigm1Cordis1Databases1Distributed Machine Learning Systems1Distributed Training1DTensor1Dynamic software composition1energy-based models1FSDP1GPU-Parallel Robot Learning1importance sampling1

Sort by

LatestMost readRecently updated

Library

Search the public knowledge base.

K
Machine LearningReinforcement LearningTransformersLLMsAttentionDiffusionAI InterpretabilityBPEcausal interventionscontext paradigm

42 results

Sort by
LatestMost readRecently updated

Tokenization for LLMs: From Raw Text to Model Inputs

Type hello, world! into an LLM. To you, that string is already meaningful: two familiar words, a comma, a space, and an exclamation ...

Large Language Modelstokenizationsubword algorithms
Sep 14, 2026 40 min read 68

Mechanistic Interpretability: Reverse-Engineering the Algorithms Inside Neural Networks

Take a simple completion: “Alice gave Bob the book because wanted it.” Suppose the model assigns a high target logit $y$ to the corr...

AI Interpretabilitymechanistic interpretabilitytransformer circuits
Sep 8, 2026 19 min read 106

World Models: Learning Enough of the Future to Act

A robot is about to push a puck across a table. There is a target marked a little farther away, and beyond it, the edge. A gentle pu...

Model-Based Reinforcement LearningWorld ModelsRobot Learning
Sep 8, 2026 26 min read 88

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

Suppose you want to train a model with a matrix optimizer such as Muon. The optimizer does not think of a weight matrix as a bag of ...

Distributed Machine Learning SystemsFSDPRaggedShard
Sep 2, 2026 20 min read 125

DeepSeek's Plugin Paradigm: Spatiotemporal Composability

A plugin registers commands, subscribes to events, allocates resources, and changes shared state. Loading is easy because the host c...

Dynamic software compositionplugin systemsrevertible effects
Aug 28, 2026 12 min read 321

Beyond Reinforcement Learning: Sampling as Optimization for Reasoning Models

Imagine an LLM solving a math problem. It samples a full reasoning trace, you run a verifier, and the verifier returns a number: per...

Machine Learningenergy-based modelsimportance sampling
Aug 28, 2026 18 min read 199

WarpSAC: When More Data Changes the Right RL Algorithm

Imagine training a robot arm from a replay buffer that contains plenty of examples of ordinary motions—move left, move right, lower ...

Reinforcement LearningSoft Actor-CriticScalable Off-Policy RL
Aug 28, 2026 25 min read 173

Attention Is All You Need: The Transformer

A diagram-rich generated explanation from the public library.

Machine LearningTransformersAttention
Aug 18, 2026 45 min read 527

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

A diagram-rich generated explanation from the public library.

Machine LearningTransformers
Aug 18, 2026 45 min read 495

B-spline Policy: Continuous Action Curves for Fast Manipulation

A diagram-rich generated explanation from the public library.

Machine Learning
Aug 4, 2026 45 min read 326

DemoSpeedup: Entropy-Guided Acceleration of Visuomotor Policy Learning

A diagram-rich generated explanation from the public library.

Machine Learning
Aug 4, 2026 45 min read 142

Backend Engineering from First Principles

Backend Engineering from first principles

Deep Dive
Aug 4, 2026 45 min read 113

From Imitation to Refinement – Residual RL for Precise Robotic Assembly

A diagram-rich generated explanation from the public library.

Reinforcement LearningDiffusion
Jun 16, 2026 45 min read 440

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

A diagram-rich generated explanation from the public library.

Machine LearningReinforcement Learning
Jun 10, 2026 45 min read 584

Imitation Bootstrapped Reinforcement Learning (IBRL)

A diagram-rich generated explanation from the public library.

Machine LearningReinforcement Learning
Jun 2, 2026 45 min read 205

AI Guardrails and Safety: From Failure Modes to Enforcement

AI guardrails and saftey

Deep Dive
May 26, 2026 45 min read 172

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

A diagram-rich generated explanation from the public library.

Deep Dive
May 26, 2026 45 min read 89

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

Harness engineering

Deep Dive
May 26, 2026 45 min read 208

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

A diagram-rich generated explanation from the public library.

Deep Dive
May 26, 2026 45 min read 93

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

A diagram-rich generated explanation from the public library.

Machine LearningReinforcement Learning
May 26, 2026 45 min read 105

KV Caching in Autoregressive Transformers

KV Caching

Machine LearningTransformersAttention
May 26, 2026 45 min read 301

Speculative Decoding: Lossless Acceleration for Large Language Models

Speculative Decoding in LLM's

LLMs
May 23, 2026 45 min read 244

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

A diagram-rich generated explanation from the public library.

Deep Dive
May 18, 2026 45 min read 296

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

A diagram-rich generated explanation from the public library.

Machine LearningReinforcement Learning
May 18, 2026 45 min read 105

ECHO: Turning Terminal Feedback into Dense Supervision for Agent RL

A diagram-rich generated explanation from the public library.

Machine LearningReinforcement Learning
May 18, 2026 45 min read 80

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

AlphaGo paper combining deep neural networks with tree search for superhuman Go play

Deep Dive
May 18, 2026 45 min read 220

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

VLA (Vision Language Action Models)

Machine Learning
May 17, 2026 45 min read 240

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

MoE architecture for efficient LLM scaling via specialized experts

Machine LearningLLMsTransformers
May 17, 2026 45 min read 158

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

RL framework that approximates maximum likelihood for binary-outcome tasks.

Machine LearningReinforcement Learning
May 17, 2026 45 min read 128

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

GRPO and RL for LLM's

Machine LearningReinforcement LearningLLMs
May 17, 2026 45 min read 152

Kubernetes Architecture and Networking in Depth

Explain Kubernetes architecture including networking in depth

Systems
May 14, 2026 45 min read 48

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

Stable JEPA-based world model that learns and plans from raw pixels.

Machine LearningReinforcement Learning
May 11, 2026 45 min read 222

Recursive Language Models: Scaling LLM Contexts via Symbolic Recursion

Language models that recursively refine or compose intermediate reasoning/representations.

Machine LearningLLMs
May 11, 2026 45 min read 88

Vector Embeddings and Vector Databases

Vector Embeddings and Vector Databases

DatabasesVector Databases
May 10, 2026 45 min read 296

Mamba-3: Improved Sequence Modeling using State Space Principles

Mamba-3: Improved Sequence Modeling using State Space Principles

Machine Learning
May 9, 2026 45 min read 139

World Models: Learning to Dream for Efficient Reinforcement Learning

World Models

Deep Dive
May 7, 2026 84 min read 150

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

Self-supervised vision model for learning image representations.

Deep Dive
May 1, 2026 87 min read 367

Transformers: Attention, Architecture, Training, and Scaling

Transformers

Machine LearningTransformersAttention
May 1, 2026 84 min read 157

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

Diffusion and flow-matching

Machine LearningDiffusion
Apr 30, 2026 87 min read 119

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

LORA Fine-tuning (Low rank adaption)

Machine LearningLoRA
Apr 29, 2026 78 min read 86

Variational Autoencoders: Principles, Derivations, and Applications

Variational auto-encoders

Deep Dive
Apr 26, 2026 84 min read 78

Policy Gradient Methods

policy gradient methods

Machine LearningReinforcement Learning
Apr 26, 2026 45 min read 94