All Episodes

Efficient Streaming Language Models with Attention Sinks (Paper Explained)

Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution (Paper Explained)

Retentive Network: A Successor to Transformer for Large Language Models (Paper Explained)

Reinforced Self-Training (ReST) for Language Modeling (Paper Explained)

[ML News] LLaMA2 Released | LLMs for Robots | Multimodality on the Rise

How Cyber Criminals Are Using ChatGPT (w/ Sergey Shykevich)

Recipe AI suggests FATAL CHLORINE GAS Recipe

DeepFloyd IF - Pixel-Based Text-to-Image Diffusion (w/ Authors)

[ML News] GPT-4 solves MIT Exam with 100% ACCURACY | OpenLLaMA 13B released

Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robust (Explained)

RWKV: Reinventing RNNs for the Transformer Era (Paper Explained)

Tree of Thoughts: Deliberate Problem Solving with Large Language Models (Full Paper Review)

OpenAI suggests AI licenses (US Senate hearing on AI regulation w/ Sam Altman)

[ML News] Geoff Hinton leaves Google | Google has NO MOAT | OpenAI down half a billion

Scaling Transformer to 1M tokens and beyond with RMT (Paper Explained)

OpenAssistant RELEASED! The world's best open-source Chat AI!

OpenAssistant First Models are here! (Open-Source ChatGPT)

The biggest week in AI (GPT-4, Office Copilot, Google PaLM, Anthropic Claude & more)

GPT-4 is here! What we know so far (Full Analysis)

This ChatGPT Skill will earn you $10B (also, AI reads your mind!)

LLaMA: Open and Efficient Foundation Language Models (Paper Explained)

Open Assistant Inference Backend Development (Hands-On Coding)

OpenAssistant - ChatGPT's Open Alternative (We need your help!)

ChatGPT: This AI has a JAILBREAK?! (Unbelievable AI Progress)

[ML News] GPT-4 Rumors | AI Mind Reading | Neuron Interaction Solved | AI Theorem Proving

CICERO: An AI agent that negotiates, persuades, and cooperates with people

[ML News] Multiplayer Stable Diffusion | OpenAI needs more funding | Text-to-Video models incoming

The New AI Model Licenses have a Legal Loophole (OpenRAIL-M of BLOOM, Stable Diffusion, etc.)

ROME: Locating and Editing Factual Associations in GPT (Paper Explained & Author Interview)

Neural Networks are Decision Trees (w/ Alexander Mattick)

This is a game changer! (AlphaTensor by DeepMind explained)

[ML News] Stable Diffusion Takes Over! (Open Source AI Art)

How to make your CPU as fast as a GPU - Advances in Sparsity w/ Nir Shavit

More Is Different for AI - Scaling Up, Emergence, and Paperclip Maximizers (w/ Jacob Steinhardt)

The hidden dangers of loading open-source AI models (ARBITRARY CODE EXPLOIT!)

The Future of AI is Self-Organizing and Self-Assembling (w/ Prof. Sebastian Risi)

The Man behind Stable Diffusion

[ML News] BLOOM: 176B Open-Source | Chinese Brain-Scale Computer | Meta AI: No Language Left Behind

JEPA - A Path Towards Autonomous Machine Intelligence (Paper Explained)

Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos (Paper Explained)

Parti - Scaling Autoregressive Models for Content-Rich Text-to-Image Generation (Paper Explained)

Did Google's LaMDA chatbot just become sentient?

[ML News] DeepMind's Flamingo Image-Text model | Locked-Image Tuning | Jurassic X & MRKL

[ML News] Meta's OPT 175B language model | DALL-E Mega is training | TorToiSe TTS fakes my voice

This A.I. creates infinite NFTs

Author Interview: SayCan - Do As I Can, Not As I Say: Grounding Language in Robotic Affordances

Do As I Can, Not As I Say: Grounding Language in Robotic Affordances (SayCan - Paper Explained)

Author Interview - ACCEL: Evolving Curricula with Regret-Based Environment Design

ACCEL: Evolving Curricula with Regret-Based Environment Design (Paper Review)

LAION-5B: 5 billion image-text-pairs dataset (with the authors)

Sparse Expert Models (Switch Transformers, GLAM, and more... w/ the Authors)

Author Interview - Transformer Memory as a Differentiable Search Index

Transformer Memory as a Differentiable Search Index (Machine Learning Research Paper Explained)

[ML News] Google's 540B PaLM Language Model & OpenAI's DALL-E 2 Text-to-Image Revolution

The Weird and Wonderful World of AI Art (w/ Author Jack Morris)

Author Interview - Improving Intrinsic Exploration with Language Abstractions

Improving Intrinsic Exploration with Language Abstractions (Machine Learning Paper Explained)

[ML News] GPT-3 learns to edit | Google Pathways | Make-A-Scene | CLIP meets GamePhysics | DouBlind

Author Interview - Memory-assisted prompt editing to improve GPT-3 after deployment

Memory-assisted prompt editing to improve GPT-3 after deployment (Machine Learning Paper Explained)

Author Interview - Typical Decoding for Natural Language Generation

Typical Decoding for Natural Language Generation (Get more human-like outputs from language models!)

One Model For All The Tasks - BLIP (Author Interview)

BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding&Generation

[ML News] AI Threatens Biological Arms Race

Active Dendrites avoid catastrophic forgetting - Interview with the Authors

Avoiding Catastrophe: Active Dendrites Enable Multi-Task Learning in Dynamic Environments (Review)

Author Interview - VOS: Learning What You Don't Know by Virtual Outlier Synthesis

VOS: Learning What You Don't Know by Virtual Outlier Synthesis (Paper Explained)

Spurious normativity enhances learning of compliance and enforcement behavior in artificial agents

First Author Interview: AI & formal math (Formal Mathematics Statement Curriculum Learning)

OpenAI tackles Math - Formal Mathematics Statement Curriculum Learning (Paper Explained)

[ML News] DeepMind controls fusion | Yann LeCun's JEPA architecture | US: AI can't copyright its art

AlphaCode - with the authors!

Competition-Level Code Generation with AlphaCode (Paper Review)

Can Wikipedia Help Offline Reinforcement Learning? (Author Interview)

Can Wikipedia Help Offline Reinforcement Learning? (Paper Explained)

[ML Olds] Meta Research Supercluster | OpenAI GPT-Instruct | Google LaMDA | Drones fight Pigeons

[ML News] Uber: Deep Learning for ETA | MuZero Video Compression | Block-NeRF | EfficientNet-X

Listening to You! - Channel Update (Author Interviews)

All about AI Accelerators: GPU, TPU, Dataflow, Near-Memory, Optical, Neuromorphic & more (w/ Author)

CM3: A Causal Masked Multimodal Model of the Internet (Paper Explained w/ Author Interview)

AI against Censorship: Genetic Algorithms, The Geneva Project, ML in Security, and more!

HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning (w/ Author)

[ML News] DeepMind AlphaCode | OpenAI math prover | Meta battles harmful content with AI

Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents (+Author)

OpenAI Embeddings (and Controversy?!)

Unsupervised Brain Models - How does Deep Learning inform Neuroscience? (w/ Patrick Mineault)

GPT-NeoX-20B - Open-Source huge language model by EleutherAI (Interview w/ co-founder Connor Leahy)

Predicting the rules behind - Deep Symbolic Regression for Recurrent Sequences (w/ author interview)

IT ARRIVED! YouTube sent me a package. (also: Limited Time Merch Deal)

[ML News] ConvNeXt: Convolutions return | China regulates algorithms | Saliency cropping examined

Dynamic Inference with Neural Interpreters (w/ author interview)

Noether Networks: Meta-Learning Useful Conserved Quantities (w/ the authors)

This Team won the Minecraft RL BASALT Challenge! (Paper Explanation & Interview with the authors)

This Team won the Minecraft RL BASALT Challenge! (Paper Explanation & Interview with the authors)

Full Self-Driving is HARD! Analyzing Elon Musk re: Tesla Autopilot on Lex Fridman's Podcast

Player of Games: All the games, one algorithm! (w/ author Martin Schmid)

GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models

[ML News] DeepMind builds Gopher | Google builds GLaM | Suicide capsule uses AI to check access

Resolution-robust Large Mask Inpainting with Fourier Convolutions (w/ Author Interview)

[ML News] DeepMind tackles Math | Microsoft does more with less | Timnit Gebru launches DAIR

NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion (ML Research Paper Explained)

[ML News] OpenAI removes GPT-3 waitlist | GauGAN2 is amazing | NYC regulates AI hiring tools

Sparse is Enough in Scaling Transformers (aka Terraformer) | ML Research Paper Explained

ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning (Paper Explained)

Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions (Paper Explained)

Peer Review is still BROKEN! The NeurIPS 2021 Review Experiment (results are in)

Parameter Prediction for Unseen Deep Architectures (w/ First Author Boris Knyazev)

Learning Rate Grafting: Transferability of Optimizer Tuning (Machine Learning Research Paper Reivew)

[ML News] Cedille French Language Model | YOU Search Engine | AI Finds Profitable MEME TOKENS

Gradients are Not All You Need (Machine Learning Research Paper Explained)

[ML News] Microsoft combines Images & Text | Meta makes artificial skin | Russians replicate DALL-E

Autoregressive Diffusion Models (Machine Learning Research Paper Explained)

[ML News] Google introduces Pathways | OpenAI solves Math Problems | Meta goes First Person

EfficientZero: Mastering Atari Games with Limited Data (Machine Learning Research Paper Explained)

[YTalks] Siraj Raval - Stories about YouTube, Plagiarism, and the Dangers of Fame (Interview)

[ML News GERMAN] NVIDIA GTC'21 | DeepMind kauft MuJoCo | Google Lernt Spreadsheet Formeln

[ML News] NVIDIA GTC'21 | DeepMind buys MuJoCo | Google predicts spreadsheet formulas

I went to an AI Art Festival in Geneva (AiiA Festival Trip Report)

Symbolic Knowledge Distillation: from General Language Models to Commonsense Models (Explained)

I took a Swiss train and it was awesome! Train Seat Review - SBB InterCity 1 - Geneva to St. Gallen

[ML News] Microsoft trains 530B model | ConvMixer model fits into single tweet | DeepMind profitable

[ML News] DeepMind does Nowcasting | The Guardian's shady reporting | AI finishes Beethoven's 10th

Grokking: Generalization beyond Overfitting on small algorithmic datasets (Paper Explained)

How far can we scale up? Deep Learning's Diminishing Returns (Article Review)

[ML News] Plagiarism Case w/ Plot Twist | CLIP for video surveillance | OpenAI summarizes books

Inconsistency in Conference Peer Review: Revisiting the 2014 NeurIPS Experiment (Paper Explained)

[ML News] New ImageNet SOTA | Uber's H3 hexagonal coordinate system | New text-image-pair dataset

Does GPT-3 lie? - Misinformation and fear-mongering around the TruthfulQA dataset

Topographic VAEs learn Equivariant Capsules (Machine Learning Research Paper Explained)

[ML News] Roomba Avoids Poop | Textless NLP | TikTok Algorithm Secrets | New Schmidhuber Blog

Celebrating 100k Subscribers! (w/ Channel Statistics)

[ML News] AI predicts race from X-Ray | Google kills HealthStreams | Boosting Search with MuZero

∞-former: Infinite Memory Transformer (aka Infty-Former / Infinity-Former, Research Paper Explained)

[ML News] Blind Chess AI Competition | Graph NNs for traffic | AI gift suggestions

ALiBi - Train Short, Test Long: Attention with linear biases enables input length extrapolation

[ML News] Stanford HAI coins Foundation Models & High-profile case of plagiarism uncovered

Fastformer: Additive Attention Can Be All You Need (Machine Learning Research Paper Explained)

PonderNet: Learning to Ponder (Machine Learning Research Paper Explained)

NeuralHash is BROKEN | How to evade Apple's detection and forge hash collisions (w/ Code)

[ML News] Nvidia renders CEO | Jurassic-1 larger than GPT-3 | Tortured Phrases reveal Plagiarism

How Apple scans your phone (and how to evade it) - NeuralHash CSAM Detection Algorithm Explained

[ML NEWS] Apple scans your phone | Master Faces beat face recognition | WALL-E is real

[ML News] AI-generated patent approved | Germany gets an analog to OpenAI | ML cheats video games

[ML News] MMO Game destroys GPUs | OpenAI quits Robotics | Today w/ guest host Sanyam Bhutani

[ML News] Facebook AI adapting robots | Baidu autonomous excavators | Happy Birthday EleutherAI

[ML News] GitHub Copilot - Copyright, GPL, Patents & more | Brickit LEGO app | Distill goes on break

Self-driving from VISION ONLY - Tesla's self-driving progress by Andrej Karpathy (Talk Analysis)

[ML News] CVPR bans social media paper promotion | AI restores Rembrandt | GPU prices down

The Dimpled Manifold Model of Adversarial Examples in Machine Learning (Research Paper Explained)

[ML News] Hugging Face course | GAN Theft Auto | AI Programming Puzzles | PyTorch 1.9 Released

XCiT: Cross-Covariance Image Transformers (Facebook AI Machine Learning Research Paper Explained)

AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control (Paper Explained)

[ML News] De-Biasing GPT-3 | RL cracks chip design | NetHack challenge | Open-Source GPT-J

Efficient and Modular Implicit Differentiation (Machine Learning Research Paper Explained)

[ML News] EU regulates AI, China trains 1.75T model, Google's oopsie, Everybody cheers for fraud.

Decision Transformer: Reinforcement Learning via Sequence Modeling (Research Paper Explained)

[ML News] Anthropic raises $124M, ML execs clueless, collusion rings, ELIZA source discovered & more

Reward Is Enough (Machine Learning Research Paper Explained)

Expire-Span: Not All Memories are Created Equal: Learning to Forget by Expiring (Paper Explained)

FNet: Mixing Tokens with Fourier Transforms (Machine Learning Research Paper Explained)

AI made this music video | What happens when OpenAI's CLIP meets BigGAN?

DDPM - Diffusion Models Beat GANs on Image Synthesis (Machine Learning Research Paper Explained)

Involution: Inverting the Inherence of Convolution for Visual Recognition (Research Paper Explained)

MLP-Mixer: An all-MLP Architecture for Vision (Machine Learning Research Paper Explained)

Is Google Translate Sexist? Gender Stereotypes in Statistical Machine Translation

Perceiver: General Perception with Iterative Attention (Google DeepMind Research Paper Explained)

Pretrained Transformers as Universal Computation Engines (Machine Learning Research Paper Explained)

Yann LeCun - Self-Supervised Learning: The Dark Matter of Intelligence (FAIR Blog Post Explained)

Multimodal Neurons in Artificial Neural Networks (w/ OpenAI Microscope, Research Paper Explained)

Machine Learning PhD Survival Guide 2021 | Advice on Topic Selection, Papers, Conferences & more!

PAIR AI Explorables | Is the problem in the data? Examples on Fairness, Diversity, and Bias.

DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning

NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis (ML Research Paper Explained)

DINO: Emerging Properties in Self-Supervised Vision Transformers (Facebook AI Research Explained)

Why AI is Harder Than We Think (Machine Learning Research Paper Explained)