Library

• What Machine Learning Is, and Is Not

  001✓ EXPLORED

  What Machine Learning Is, and Is Not

• The Data Is the Model

  002✓ EXPLORED

  The Data Is the Model

• Features and Representations

  003✓ EXPLORED

  Features and Representations

• Loss: How a Model Knows It Is Wrong

  004✓ EXPLORED

  Loss: How a Model Knows It Is Wrong

• Gradient Descent

  005✓ EXPLORED

  Gradient Descent

• Backpropagation

  006✓ EXPLORED

  Backpropagation

• What a Neural Network Actually Computes

  007✓ EXPLORED

  What a Neural Network Actually Computes

• Parameters, Weights, Layers, Activations

  008✓ EXPLORED

  Parameters, Weights, Layers, Activations

• Activations: ReLU, GELU, SwiGLU

  009✓ EXPLORED

  Activations: ReLU, GELU, SwiGLU

• Training Versus Inference

  010✓ EXPLORED

  Training Versus Inference

• Self-Supervised Learning

  011✓ EXPLORED

  Self-Supervised Learning

• Overfitting and Generalisation

  012✓ EXPLORED

  Overfitting and Generalisation

• Residual Connections and Normalisation

  013✓ EXPLORED

  Residual Connections and Normalisation

• Why Scale Worked

  014✓ EXPLORED

  Why Scale Worked

• Why Hand-Built Knowledge Lost

  015✓ EXPLORED

  Why Hand-Built Knowledge Lost

• Turning Text Into Numbers

  016✓ EXPLORED

  Turning Text Into Numbers

• Tokens: How Language Becomes Something a Model Can Process

  017✓ EXPLORED

  Tokens: How Language Becomes Something a Model Can Process

• Byte Pair Encoding

  018✓ EXPLORED

  Byte Pair Encoding

• What Tokenisation Breaks

  019✓ EXPLORED

  What Tokenisation Breaks

• Embeddings: Meaning as Direction

  020✓ EXPLORED

  Embeddings: Meaning as Direction

• Living in 4,096 Dimensions

  021✓ EXPLORED

  Living in 4,096 Dimensions

• Predicting the Next Token

  022✓ EXPLORED

  Predicting the Next Token

• The Recurrent Era and Its Bottleneck

  023✓ EXPLORED

  The Recurrent Era and Its Bottleneck

• One Word, Many Meanings

  024✓ EXPLORED

  One Word, Many Meanings

• Vocabularies, Special Tokens and Chat Templates

  025✓ EXPLORED

  Vocabularies, Special Tokens and Chat Templates

• Attention, Before the Maths

  026✓ EXPLORED

  Attention, Before the Maths

• Queries, Keys and Values

  027✓ EXPLORED

  Queries, Keys and Values

• Self-Attention, Step by Step

  028✓ EXPLORED

  Self-Attention, Step by Step

• Multi-Head Attention

  029✓ EXPLORED

  Multi-Head Attention

• The Causal Mask

  030✓ EXPLORED

  The Causal Mask

• Position: Attention Has No Sense of Order

  031✓ EXPLORED

  Position: Attention Has No Sense of Order

• Rotary Position Embeddings

  032✓ EXPLORED

  Rotary Position Embeddings

• Models Without Positional Encoding

  033✓ EXPLORED

  Models Without Positional Encoding

• The Feedforward Block

  034✓ EXPLORED

  The Feedforward Block

• The Transformer Block, Assembled

  035✓ EXPLORED

  The Transformer Block, Assembled

• The Residual Stream

  036✓ EXPLORED

  The Residual Stream

• Encoder, Decoder, or Both

  037✓ EXPLORED

  Encoder, Decoder, or Both

• Why Attention Gets Expensive

  038✓ EXPLORED

  Why Attention Gets Expensive

• FlashAttention

  039✓ EXPLORED

  FlashAttention

• Multi-Query and Grouped-Query Attention

  040✓ EXPLORED

  Multi-Query and Grouped-Query Attention

• Alternatives to Attention

  041✓ EXPLORED

  Alternatives to Attention

• Logits and the Softmax

  042✓ EXPLORED

  Logits and the Softmax

• Temperature

  043✓ EXPLORED

  Temperature

• Top-k, Top-p and Min-p

  044✓ EXPLORED

  Top-k, Top-p and Min-p

• The Context Window

  045✓ EXPLORED

  The Context Window

• Long Context Is Not Uniform Attention

  046✓ EXPLORED

  Long Context Is Not Uniform Attention

• The KV Cache

  047✓ EXPLORED

  The KV Cache

• Prefill Versus Decode

  048✓ EXPLORED

  Prefill Versus Decode

• Batching, Throughput and Latency

  049✓ EXPLORED

  Batching, Throughput and Latency

• Speculative Decoding

  050✓ EXPLORED

  Speculative Decoding

• Constrained and Structured Generation

  051✓ EXPLORED

  Constrained and Structured Generation

• System Prompts and Instruction Hierarchy

  052✓ EXPLORED

  System Prompts and Instruction Hierarchy

• Pretraining

  053✓ EXPLORED

  Pretraining

• What Goes Into the Corpus

  054✓ EXPLORED

  What Goes Into the Corpus

• Chinchilla and Compute-Optimal Training

  055✓ EXPLORED

  Chinchilla and Compute-Optimal Training

• Supervised Fine-Tuning

  056✓ EXPLORED

  Supervised Fine-Tuning

• RLHF

  057✓ EXPLORED

  RLHF

• DPO and Direct Preference Learning

  058✓ EXPLORED

  DPO and Direct Preference Learning

• Training Against Written Principles

  059✓ EXPLORED

  Training Against Written Principles

• LoRA and Parameter-Efficient Fine-Tuning

  060✓ EXPLORED

  LoRA and Parameter-Efficient Fine-Tuning

• Fine-Tune, Prompt, or Retrieve

  061✓ EXPLORED

  Fine-Tune, Prompt, or Retrieve

• Catastrophic Forgetting

  062✓ EXPLORED

  Catastrophic Forgetting

• The Emergent Abilities Argument

  063✓ EXPLORED

  The Emergent Abilities Argument

• Chain of Thought

  064✓ EXPLORED

  Chain of Thought

• Sampling Many Answers

  065✓ EXPLORED

  Sampling Many Answers

• Test-Time Compute

  066✓ EXPLORED

  Test-Time Compute

• Reasoning Models

  067✓ EXPLORED

  Reasoning Models

• Mixture of Experts

  068✓ EXPLORED

  Mixture of Experts

• Dense Versus Sparse Models

  069✓ EXPLORED

  Dense Versus Sparse Models

• Distillation

  070✓ EXPLORED

  Distillation

• Pruning

  071✓ EXPLORED

  Pruning

• Looking Inside the Model

  072✓ EXPLORED

  Looking Inside the Model

• Architectural Limits

  073✓ EXPLORED

  Architectural Limits

• Why GPUs

  074✓ EXPLORED

  Why GPUs

• VRAM: The Number That Decides Everything

  075✓ EXPLORED

  VRAM: The Number That Decides Everything

• Bandwidth, Not FLOPs

  076✓ EXPLORED

  Bandwidth, Not FLOPs

• Unified Memory

  077✓ EXPLORED

  Unified Memory

• Quantisation

  078✓ EXPLORED

  Quantisation

• GPTQ, AWQ and K-Quants

  079✓ EXPLORED

  GPTQ, AWQ and K-Quants

• Model Formats: GGUF, Safetensors, MLX

  080✓ EXPLORED

  Model Formats: GGUF, Safetensors, MLX

• Running an Open-Weight Model Locally

  081✓ EXPLORED

  Running an Open-Weight Model Locally

• Why Long Context Eats Your RAM

  082✓ EXPLORED

  Why Long Context Eats Your RAM

• Splitting a Model Across Machines

  083✓ EXPLORED

  Splitting a Model Across Machines

• A Cluster of Personal Computers

  084✓ EXPLORED

  A Cluster of Personal Computers

• Local Versus Cloud, Honestly

  085✓ EXPLORED

  Local Versus Cloud, Honestly

• Embedding Models

  086✓ EXPLORED

  Embedding Models

• Vector Search

  087✓ EXPLORED

  Vector Search

• Retrieval-Augmented Generation

  088✓ EXPLORED

  Retrieval-Augmented Generation

• Chunking and Reranking

  089✓ EXPLORED

  Chunking and Reranking

• Tool Use and Function Calling

  090✓ EXPLORED

  Tool Use and Function Calling

• Agents

  091✓ EXPLORED

  Agents

• Standardised Tool Connections

  092✓ EXPLORED

  Standardised Tool Connections

• Multimodal Models

  093✓ EXPLORED

  Multimodal Models

• Diffusion and Image Generation

  094✓ EXPLORED

  Diffusion and Image Generation

• Speech Recognition and Synthesis

  095✓ EXPLORED

  Speech Recognition and Synthesis

• Hallucination

  096✓ EXPLORED

  Hallucination

• Evaluating Models

  097✓ EXPLORED

  Evaluating Models

• Bias, Harm and Safety Training

  098✓ EXPLORED

  Bias, Harm and Safety Training

• Prompt Injection

  099✓ EXPLORED

  Prompt Injection

• Open Weights, Closed Frontiers

  100✓ EXPLORED

  Open Weights, Closed Frontiers

• Neural Tangent Kernel Analysis

  101✓ EXPLORED

  Neural Tangent Kernel Analysis

• Diffusion Model ODE/SDE Frameworks

  102✓ EXPLORED

  Diffusion Model ODE/SDE Frameworks

• Sparse Mixture of Experts Routing

  103✓ EXPLORED

  Sparse Mixture of Experts Routing

• Transformer Neural Machine Translation

  104✓ EXPLORED

  Transformer Neural Machine Translation

  JUNE 2017

• Vision-Language Navigation

  105✓ EXPLORED

  Vision-Language Navigation

• Model-Based Reinforcement Learning with MuZero

  106✓ EXPLORED

  Model-Based Reinforcement Learning with MuZero

• BIG-bench Collaborative Benchmark

  107✓ EXPLORED

  BIG-bench Collaborative Benchmark

• Mechanistic Probes for Circuit Discovery

  108✓ EXPLORED

  Mechanistic Probes for Circuit Discovery

• Blockwise Quantization-Aware Training

  109✓ EXPLORED

  Blockwise Quantization-Aware Training

• Dataset Distillation

  110✓ EXPLORED

  Dataset Distillation

• AI and Neuroscience Cross-Pollination

  111✓ EXPLORED

  AI and Neuroscience Cross-Pollination

• Layer-wise Adaptive Rate Scaling (LARS)

  112✓ EXPLORED

  Layer-wise Adaptive Rate Scaling (LARS)

• vLLM: PagedAttention for LLM Serving

  113✓ EXPLORED

  vLLM: PagedAttention for LLM Serving

• Unified MultiModal Embedding with ImageBind

  114✓ EXPLORED

  Unified MultiModal Embedding with ImageBind

• Hindsight Experience Replay

  115✓ EXPLORED

  Hindsight Experience Replay

• Holistic Evaluation of Language Models (HELM)

  116✓ EXPLORED

  Holistic Evaluation of Language Models (HELM)

• Sparse Autoencoders for Feature Discovery

  117✓ EXPLORED

  Sparse Autoencoders for Feature Discovery

• Sliding Window Attention for Long Sequences

  118✓ EXPLORED

  Sliding Window Attention for Long Sequences

• Web-Scale Text Corpora Curation

  119✓ EXPLORED

  Web-Scale Text Corpora Curation

• Graph Attention Networks

  120✓ EXPLORED

  Graph Attention Networks

• Fourier Features for Positional Encoding

  121✓ EXPLORED

  Fourier Features for Positional Encoding

• Orca: System for Distributed Inference

  122✓ EXPLORED

  Orca: System for Distributed Inference

• Audio-Visual Contrastive Learning

  123✓ EXPLORED

  Audio-Visual Contrastive Learning

• Self-Play with Population-Based Training

  124✓ EXPLORED

  Self-Play with Population-Based Training

• Anthropic's Redwood Research Interpretability

  125✓ EXPLORED

  Anthropic's Redwood Research Interpretability

• TruthfulQA: Measuring Truthfulness

  126✓ EXPLORED

  TruthfulQA: Measuring Truthfulness

• Causal Mediation Analysis in Neural Networks

  127✓ EXPLORED

  Causal Mediation Analysis in Neural Networks

• Activation Sparsity via ReLU Pruning

  128✓ EXPLORED

  Activation Sparsity via ReLU Pruning

• Crowdsourcing High-Quality Human Feedback

  129✓ EXPLORED

  Crowdsourcing High-Quality Human Feedback

• BERT and the Masked Language Modeling Revolution

  130✓ EXPLORED

  BERT and the Masked Language Modeling Revolution

• Stable Diffusion Architecture

  131✓ EXPLORED

  Stable Diffusion Architecture

• Hyperparameter Transfer Learning

  132✓ EXPLORED

  Hyperparameter Transfer Learning

• TensorRT and Kernel Fusion

  133✓ EXPLORED

  TensorRT and Kernel Fusion

• NeRF: Neural Radiance Fields

  134✓ EXPLORED

  NeRF: Neural Radiance Fields

• Mixture of Experts Routing

  135✓ EXPLORED

  Mixture of Experts Routing

• Sparse Transformer with Local Attention

  136✓ EXPLORED

  Sparse Transformer with Local Attention

• Low-Rank Adaptation (LoRA)

  137✓ EXPLORED

  Low-Rank Adaptation (LoRA)

• Gradient Checkpointing for Memory-Efficient Training

  138✓ EXPLORED

  Gradient Checkpointing for Memory-Efficient Training

• Model Soups: Weight Averaging for Improved Robustness

  139✓ EXPLORED

  Model Soups: Weight Averaging for Improved Robustness

• Manifold Mixup for Better Representations

  140✓ EXPLORED

  Manifold Mixup for Better Representations

• Speculative Decoding for Faster LLM Inference

  141✓ EXPLORED

  Speculative Decoding for Faster LLM Inference

• Multimodal Chain-of-Thought Reasoning

  142✓ EXPLORED

  Multimodal Chain-of-Thought Reasoning

• Preference Optimization via Nash Learning

  143✓ EXPLORED

  Preference Optimization via Nash Learning

• Red Teaming with Language Models

  144✓ EXPLORED

  Red Teaming with Language Models

• Mechanistic Interpretability of Induction Heads

  145✓ EXPLORED

  Mechanistic Interpretability of Induction Heads

• Extreme Low-Bit Post-Training Quantization

  146✓ EXPLORED

  Extreme Low-Bit Post-Training Quantization

• Data Selection via Perplexity for Language Model Training

  147✓ EXPLORED

  Data Selection via Perplexity for Language Model Training

• The Deep Learning Hardware Revolution

  148✓ EXPLORED

  The Deep Learning Hardware Revolution

• Vector-Quantized Variational Autoencoders (VQ-VAE)

  149✓ EXPLORED

  Vector-Quantized Variational Autoencoders (VQ-VAE)

• Gradient-Based Meta-Learning (MAML)

  150✓ EXPLORED

  Gradient-Based Meta-Learning (MAML)

• Sharpness-Aware Minimization (SAM)

  151✓ EXPLORED

  Sharpness-Aware Minimization (SAM)

• Paged Attention for Efficient Memory Management

  152✓ EXPLORED

  Paged Attention for Efficient Memory Management

• Unified Embedding Space for All Modalities

  153✓ EXPLORED

  Unified Embedding Space for All Modalities

• Multi-Agent Deep Reinforcement Learning with Centralized Critics

  154✓ EXPLORED

  Multi-Agent Deep Reinforcement Learning with Centralized Critics

• Scalable Oversight via Recursive Reward Modeling

  155✓ EXPLORED

  Scalable Oversight via Recursive Reward Modeling

• Benchmarking Hallucination in Language Models

  156✓ EXPLORED

  Benchmarking Hallucination in Language Models

• Activation Compression via Quantized Training

  157✓ EXPLORED

  Activation Compression via Quantized Training

• Deduplication of Massive Training Datasets

  158✓ EXPLORED

  Deduplication of Massive Training Datasets

• The Transformer Architecture Paper

  159✓ EXPLORED

  The Transformer Architecture Paper

• Recurrent Independent Mechanisms

  160✓ EXPLORED

  Recurrent Independent Mechanisms

• Self-Supervised Learning of Visual Features via Contrastive Loss

  161✓ EXPLORED

  Self-Supervised Learning of Visual Features via Contrastive Loss

• AdaFactor: Adaptive Learning Rates with Sublinear Memory

  162✓ EXPLORED

  AdaFactor: Adaptive Learning Rates with Sublinear Memory

• Continuous Batching in LLM Serving

  163✓ EXPLORED

  Continuous Batching in LLM Serving

• Compositional Visual Reasoning with Neural Module Networks

  164✓ EXPLORED

  Compositional Visual Reasoning with Neural Module Networks

• Reward Model Overoptimization

  165✓ EXPLORED

  Reward Model Overoptimization

• TruthfulQA: Benchmarking Tendency to Generate Falsehoods

  166✓ EXPLORED

  TruthfulQA: Benchmarking Tendency to Generate Falsehoods

• Causal Abstraction for Model Verification

  167✓ EXPLORED

  Causal Abstraction for Model Verification

• Sliding Window Attention for Infinite Context

  168✓ EXPLORED

  Sliding Window Attention for Infinite Context

• Model Contamination Detection in Benchmarks

  169✓ EXPLORED

  Model Contamination Detection in Benchmarks

• The Bitter Lesson of Compute and Scale

  170✓ EXPLORED

  The Bitter Lesson of Compute and Scale

• Vision Transformer (ViT) Scaling

  171✓ EXPLORED

  Vision Transformer (ViT) Scaling

• Gradient Surgery for Multi-Task Learning

  172✓ EXPLORED

  Gradient Surgery for Multi-Task Learning

• Sparse Mixture of Experts Inference Routing

  173✓ EXPLORED

  Sparse Mixture of Experts Inference Routing

• Neural Tangent Kernel Theory for Wide Networks

  174✓ EXPLORED

  Neural Tangent Kernel Theory for Wide Networks

• Transformer Memory Compression via Sliding Windows

  175✓ EXPLORED

  Transformer Memory Compression via Sliding Windows

• Neural Radiance Fields for 3D Reconstruction

  176✓ EXPLORED

  Neural Radiance Fields for 3D Reconstruction

• Soft Actor-Critic with Maximum Entropy

  177✓ EXPLORED

  Soft Actor-Critic with Maximum Entropy

• Red Teaming for Language Model Safety

  178✓ EXPLORED

  Red Teaming for Language Model Safety

• Benchmarking Compositional Generalization

  179✓ EXPLORED

  Benchmarking Compositional Generalization

• Mechanistic Interpretability of Grokking

  180✓ EXPLORED

  Mechanistic Interpretability of Grokking

• Speculative Decoding for Faster Inference

  181✓ EXPLORED

  Speculative Decoding for Faster Inference

• Text-to-3D Generation with Score Distillation

  182✓ EXPLORED

  Text-to-3D Generation with Score Distillation

• Human Feedback from Comparisons

  183✓ EXPLORED

  Human Feedback from Comparisons

• Mixture Density Networks for Uncertainty

  184✓ EXPLORED

  Mixture Density Networks for Uncertainty

• Coresets for Efficient Dataset Summarization

  185✓ EXPLORED

  Coresets for Efficient Dataset Summarization

• Knowledge Distillation from Multiple Teachers

  186✓ EXPLORED

  Knowledge Distillation from Multiple Teachers

• Weight Agnostic Neural Architecture Search

  187✓ EXPLORED

  Weight Agnostic Neural Architecture Search

• Deep Double Descent: Beyond U-Shaped Risk

  188✓ EXPLORED

  Deep Double Descent: Beyond U-Shaped Risk

• Volumetric Rendering with Neural Graphics Primitives

  189✓ EXPLORED

  Volumetric Rendering with Neural Graphics Primitives

• Multi-Task Learning with Task Balancing

  190✓ EXPLORED

  Multi-Task Learning with Task Balancing

• Efficient ViT with Shifted Windows

  191✓ EXPLORED

  Efficient ViT with Shifted Windows

• No-Regret Online Learning to Nash Equilibrium

  192✓ EXPLORED

  No-Regret Online Learning to Nash Equilibrium

• Model Parallelism with Pipeline Bubbles

  193✓ EXPLORED

  Model Parallelism with Pipeline Bubbles

• Video Diffusion with Temporal Consistency

  194✓ EXPLORED

  Video Diffusion with Temporal Consistency

• Recursive Reward Modeling for Scalable Oversight

  195✓ EXPLORED

  Recursive Reward Modeling for Scalable Oversight

• Out-of-Distribution Detection via Likelihood Ratios

  196✓ EXPLORED

  Out-of-Distribution Detection via Likelihood Ratios

• Causal Abstraction via Interchange Interventions

  197✓ EXPLORED

  Causal Abstraction via Interchange Interventions

• Quantization with Learned Rounding

  198✓ EXPLORED

  Quantization with Learned Rounding

• Data Valuation with Shapley Values

  199✓ EXPLORED

  Data Valuation with Shapley Values

• Transformer Positional Encoding Alternatives

  200✓ EXPLORED

  Transformer Positional Encoding Alternatives

• Memory-Efficient Backpropagation with Reversible Layers

  201✓ EXPLORED

  Memory-Efficient Backpropagation with Reversible Layers

• Audio-Driven Talking Head Generation

  202✓ EXPLORED

  Audio-Driven Talking Head Generation

• Constitutional AI for Harmless Assistance

  203✓ EXPLORED

  Constitutional AI for Harmless Assistance

• Adversarial Evaluation of Multimodal Reasoning

  204✓ EXPLORED

  Adversarial Evaluation of Multimodal Reasoning

• Sparse Autoencoders for Dictionary Learning

  205✓ EXPLORED

  Sparse Autoencoders for Dictionary Learning

• Dynamic Quantization During Serving

  206✓ EXPLORED

  Dynamic Quantization During Serving

• Synthetic Data Generation with Differential Privacy

  207✓ EXPLORED

  Synthetic Data Generation with Differential Privacy

• History: The 2012 AlexNet Revolution

  208✓ EXPLORED

  History: The 2012 AlexNet Revolution

• Graph Transformers with Structural Encodings

  209✓ EXPLORED

  Graph Transformers with Structural Encodings

• Optimization Theory for Adaptive Gradient Methods

  210✓ EXPLORED

  Optimization Theory for Adaptive Gradient Methods

• Multi-Task Reinforcement Learning with Shared Representations

  211✓ EXPLORED

  Multi-Task Reinforcement Learning with Shared Representations

• Differentiable Architecture Search

  212✓ EXPLORED

  Differentiable Architecture Search

• Mixture of Experts: Sparse Routing at Scale

  213✓ EXPLORED

  Mixture of Experts: Sparse Routing at Scale

• Retentive Networks for Long Sequences

  214✓ EXPLORED

  Retentive Networks for Long Sequences

• State Space Models for Long Sequences

  215✓ EXPLORED

  State Space Models for Long Sequences

• Differential Privacy by Noising Gradients

  216✓ EXPLORED

  Differential Privacy by Noising Gradients

• Progressive Growing of GANs

  217✓ EXPLORED

  Progressive Growing of GANs

• Meta-Learning with External Memory

  218✓ EXPLORED

  Meta-Learning with External Memory

• Loss Landscapes: Flat Minima and Sharp Ones

  219✓ EXPLORED

  Loss Landscapes: Flat Minima and Sharp Ones

• The Information Bottleneck

  220✓ EXPLORED

  The Information Bottleneck

• The Lottery Ticket Hypothesis

  221✓ EXPLORED

  The Lottery Ticket Hypothesis

• The Neural Tangent Kernel

  222✓ EXPLORED

  The Neural Tangent Kernel

• Feature Learning: The Lazy-to-Rich Transition

  223✓ EXPLORED

  Feature Learning: The Lazy-to-Rich Transition

• Emergence: Abilities That Appear Only With Scale

  224✓ EXPLORED

  Emergence: Abilities That Appear Only With Scale

• KV Cache Compression for Long Context

  225✓ EXPLORED

  KV Cache Compression for Long Context

• Predictive Auto-Scaling for Model Serving

  226✓ EXPLORED

  Predictive Auto-Scaling for Model Serving

• Elastic Training: Surviving a Lost Machine

  227✓ EXPLORED

  Elastic Training: Surviving a Lost Machine

• near‑data‑processing-for-embedding-lookup

  228✓ EXPLORED

  near‑data‑processing-for-embedding-lookup

• Contrastive Learning Across Vision, Audio and Text

  229✓ EXPLORED

  Contrastive Learning Across Vision, Audio and Text

• Vision-Language-Action Models for Robotics

  230✓ EXPLORED

  Vision-Language-Action Models for Robotics

• World Models: Planning Inside a Learned Simulator

  231✓ EXPLORED

  World Models: Planning Inside a Learned Simulator

• Imitation Learning from Observation

  232✓ EXPLORED

  Imitation Learning from Observation

• Model-Based RL and the Limits of a Learned Simulator

  233✓ EXPLORED

  Model-Based RL and the Limits of a Learned Simulator

• Inverse Reinforcement Learning

  234✓ EXPLORED

  Inverse Reinforcement Learning

• Trojans and Backdoors: Models with Hidden Triggers

  235✓ EXPLORED

  Trojans and Backdoors: Models with Hidden Triggers

• evaluation-with-adversarial-n‑way-forcing

  236✓ EXPLORED

  evaluation-with-adversarial-n‑way-forcing

• Calibration: When Confidence Matches Correctness

  237✓ EXPLORED

  Calibration: When Confidence Matches Correctness

• Probing for Linguistic Knowledge

  238✓ EXPLORED

  Probing for Linguistic Knowledge

• Ablation: Reading Function by Removing Parts

  239✓ EXPLORED

  Ablation: Reading Function by Removing Parts

• LoRA: Low-Rank Fine-Tuning

  240✓ EXPLORED

  LoRA: Low-Rank Fine-Tuning

• Synthetic Data for Data-Scarce Domains

  241✓ EXPLORED

  Synthetic Data for Data-Scarce Domains

• Active Learning: Choosing What to Label

  242✓ EXPLORED

  Active Learning: Choosing What to Label

• Cleaning Web-Scale Training Data

  243✓ EXPLORED

  Cleaning Web-Scale Training Data

• Connectionism versus Symbolism

  244✓ EXPLORED

  Connectionism versus Symbolism

• The Rise of Self-Supervised Learning

  245✓ EXPLORED

  The Rise of Self-Supervised Learning

• Vision-Transformer Hybrid Architectures

  246✓ EXPLORED

  Vision-Transformer Hybrid Architectures

• MoE Routing Strategies

  247✓ EXPLORED

  MoE Routing Strategies

• Model Merging via Weight Interpolation

  248✓ EXPLORED

  Model Merging via Weight Interpolation

• Mechanistic Interpretability of In-Context Learning

  249✓ EXPLORED

  Mechanistic Interpretability of In-Context Learning

• Retentive Networks (RetNet)

  250✓ EXPLORED

  Retentive Networks (RetNet)

• JEPA and I-JEPA

  251✓ EXPLORED

  JEPA and I-JEPA

• Preference Optimization with DPO

  252✓ EXPLORED

  Preference Optimization with DPO

• Temporal Difference Learning Theory

  253✓ EXPLORED

  Temporal Difference Learning Theory

• Memorization vs. Generalization in Large Models

  254✓ EXPLORED

  Memorization vs. Generalization in Large Models

• Model-Based RL with Learned Dynamics

  255✓ EXPLORED

  Model-Based RL with Learned Dynamics

• FP8 Training and Inference

  256UNOPENED

  FP8 Training and Inference

• Scaling Laws for Transfer

  257UNOPENED

  Scaling Laws for Transfer

• Diffusion Transformers (DiT)

  258UNOPENED

  Diffusion Transformers (DiT)

• Conformal Prediction for LLMs

  259UNOPENED

  Conformal Prediction for LLMs

• Parallel Context Windows

  260UNOPENED

  Parallel Context Windows

• Offline RL with Conservative Q-Learning

  261✓ EXPLORED

  Offline RL with Conservative Q-Learning

• Tool-Integrated Language Agents

  262UNOPENED

  Tool-Integrated Language Agents

• Gated Linear Units

  263UNOPENED

  Gated Linear Units

• Dataset Poisoning Attacks

  264UNOPENED

  Dataset Poisoning Attacks

• Hypernetworks for Parameter Generation

  265UNOPENED

  Hypernetworks for Parameter Generation

• Learning from Positive-Unlabeled Data

  266UNOPENED

  Learning from Positive-Unlabeled Data

• Optimal Transport for Domain Adaptation

  267UNOPENED

  Optimal Transport for Domain Adaptation

• Conditional Computation with Mixture-of-Experts

  268UNOPENED

  Conditional Computation with Mixture-of-Experts

• Emergent World Models in RL

  269UNOPENED

  Emergent World Models in RL

• Soft Prompt Tuning

  270UNOPENED

  Soft Prompt Tuning

• Gradient Compression for Distributed Training

  271UNOPENED

  Gradient Compression for Distributed Training

• Nonparametric Bayesian Deep Learning

  272UNOPENED

  Nonparametric Bayesian Deep Learning

• Neural Architecture Search with Weight Sharing

  273UNOPENED

  Neural Architecture Search with Weight Sharing

• Dynamic Evaluation of Language Models

  274UNOPENED

  Dynamic Evaluation of Language Models

• Feature Visualization with Multidimensional Scaling

  275UNOPENED

  Feature Visualization with Multidimensional Scaling

• Sparse Transformers with Factorized Attention

  276UNOPENED

  Sparse Transformers with Factorized Attention

• Perceiver IO: General Perception with Iterative Attention

  277UNOPENED

  Perceiver IO: General Perception with Iterative Attention

• Mixture of Depths: Dynamically Allocating Compute

  278UNOPENED

  Mixture of Depths: Dynamically Allocating Compute

• Monarch Matrices for Efficient Linear Layers

  279UNOPENED

  Monarch Matrices for Efficient Linear Layers

• Kernel Methods Meet Transformers

  280UNOPENED

  Kernel Methods Meet Transformers

• Neural Tangent Kernel Theory for Deep Learning

  281UNOPENED

  Neural Tangent Kernel Theory for Deep Learning

• Grokking: Generalization Beyond Overfitting

  282UNOPENED

  Grokking: Generalization Beyond Overfitting

• RL from Imperfect Human Feedback

  283UNOPENED

  RL from Imperfect Human Feedback

• PagedAttention for Efficient KV Cache Management

  284UNOPENED

  PagedAttention for Efficient KV Cache Management

• Retentive Networks as a Transformer Alternative

  285UNOPENED

  Retentive Networks as a Transformer Alternative

• Mamba: Selective State Space Models

  286UNOPENED

  Mamba: Selective State Space Models

• RLHF vs. DPO: Direct Preference Optimization

  287UNOPENED

  RLHF vs. DPO: Direct Preference Optimization

• Lion Optimizer: Sign-based Adaptive Learning

  288UNOPENED

  Lion Optimizer: Sign-based Adaptive Learning

• MuJoCo and the Physics-Based RL Benchmark

  289UNOPENED

  MuJoCo and the Physics-Based RL Benchmark

• Beyond Accuracy: Calibration and ECE

  290UNOPENED

  Beyond Accuracy: Calibration and ECE

• LoRA: Low-Rank Adaptation of Large Models

  291UNOPENED

  LoRA: Low-Rank Adaptation of Large Models

• Data Management for Lifelong Learning

  292UNOPENED

  Data Management for Lifelong Learning

• Weak-to-Strong Generalization

  293UNOPENED

  Weak-to-Strong Generalization

• Superposition and Polysemantic Neurons

  294UNOPENED

  Superposition and Polysemantic Neurons

• The Bitter Lesson of Search and Learning

  295UNOPENED

  The Bitter Lesson of Search and Learning

• Intrinsic Dimension of Model Manifolds

  296UNOPENED

  Intrinsic Dimension of Model Manifolds

• Cross-Modal Retrieval with Contrastive Pre-training

  297UNOPENED

  Cross-Modal Retrieval with Contrastive Pre-training

• Amortized Bayesian Inference with Normalizing Flows

  298UNOPENED

  Amortized Bayesian Inference with Normalizing Flows

• Self-Supervised Learning of Visual Representations

  299UNOPENED

  Self-Supervised Learning of Visual Representations

• Adversarial Attacks on Semantic Segmentation

  300UNOPENED

  Adversarial Attacks on Semantic Segmentation

• Simulated Annealing for Architecture Search

  301UNOPENED

  Simulated Annealing for Architecture Search

• Quantization of Activations with Dynamic Ranges

  302UNOPENED

  Quantization of Activations with Dynamic Ranges

• Temporal Difference Learning in Deep RL

  303UNOPENED

  Temporal Difference Learning in Deep RL

• Information Bottleneck in Deep Learning

  304UNOPENED

  Information Bottleneck in Deep Learning

• Transformer Inductive Bias Analysis

  305UNOPENED

  Transformer Inductive Bias Analysis

• Reward Modeling with Human Feedback

  306UNOPENED

  Reward Modeling with Human Feedback

• Mechanistic Interpretability of Attention Heads

  307UNOPENED

  Mechanistic Interpretability of Attention Heads

• Sliding Window Attention

  308UNOPENED

  Sliding Window Attention

• Data Scarcity with Synthetic Pre-training

  309UNOPENED

  Data Scarcity with Synthetic Pre-training

• The Stochastic Gradient Descent Revolution

  310UNOPENED

  The Stochastic Gradient Descent Revolution

• Mixture of Experts Routing Strategies

  311UNOPENED

  Mixture of Experts Routing Strategies

• Gradient Checkpointing for Memory Efficiency

  312UNOPENED

  Gradient Checkpointing for Memory Efficiency

• Implicit Gradient Regularization

  313UNOPENED

  Implicit Gradient Regularization

• Grokkking Phenomenon Analysis

  314UNOPENED

  Grokkking Phenomenon Analysis

• KV Cache Compression

  315UNOPENED

  KV Cache Compression

• Visual Question Answering with External Knowledge

  316UNOPENED

  Visual Question Answering with External Knowledge

• Interpretable Reward Functions

  317UNOPENED

  Interpretable Reward Functions

• Measuring Neural Network Calibration

  318UNOPENED

  Measuring Neural Network Calibration

• Causal Mediation Analysis in Vision Models

  319UNOPENED

  Causal Mediation Analysis in Vision Models

• Adaptive Computation Time

  320UNOPENED

  Adaptive Computation Time

• Perceptron to Deep Learning Transition

  321UNOPENED

  Perceptron to Deep Learning Transition

• State Space Models for Long Sequences

  322UNOPENED

  State Space Models for Long Sequences

• ZeRO: Zero Redundancy Optimizer

  323UNOPENED

  ZeRO: Zero Redundancy Optimizer

• Second Order Optimization for Deep Learning

  324UNOPENED

  Second Order Optimization for Deep Learning

• Model Parallelism Strategies

  325UNOPENED

  Model Parallelism Strategies

• Audio-Visual Speech Separation

  326UNOPENED

  Audio-Visual Speech Separation

• Exploration with Intrinsic Curiosity

  327UNOPENED

  Exploration with Intrinsic Curiosity

• AI Deception Detection and Prevention

  328UNOPENED

  AI Deception Detection and Prevention

• Adversarial Evaluation of Reasoning

  329UNOPENED

  Adversarial Evaluation of Reasoning

• Representation Similarity Analysis

  330UNOPENED

  Representation Similarity Analysis

• Dynamic Sparsity During Training

  331UNOPENED

  Dynamic Sparsity During Training

• Graph Neural Networks for Relational Reasoning

  332UNOPENED

  Graph Neural Networks for Relational Reasoning

• Meta-Learning Initializations

  333UNOPENED

  Meta-Learning Initializations

• Neural Architecture Search Fundamentals

  334UNOPENED

  Neural Architecture Search Fundamentals

• Neural Architecture Search with Differentiable Supernets

  335UNOPENED

  Neural Architecture Search with Differentiable Supernets

• Sparse Mixture-of-Experts for Trillion-Parameter Models

  336UNOPENED

  Sparse Mixture-of-Experts for Trillion-Parameter Models

• Hybrid CNN-Transformer Architectures

  337UNOPENED

  Hybrid CNN-Transformer Architectures

• Meta-Learning for Fast Adaptation (MAML)

  338UNOPENED

  Meta-Learning for Fast Adaptation (MAML)

• Self-Supervised Learning via Contrastive Predictive Coding

  339UNOPENED

  Self-Supervised Learning via Contrastive Predictive Coding

• Adaptive Gradient Methods with Dynamic Bound

  340UNOPENED

  Adaptive Gradient Methods with Dynamic Bound

• KV Cache Quantization and Management

  341UNOPENED

  KV Cache Quantization and Management

• Learning Joint Embeddings for Vision and Language

  342UNOPENED

  Learning Joint Embeddings for Vision and Language

• Model-Based Reinforcement Learning with Learned Dynamics

  343UNOPENED

  Model-Based Reinforcement Learning with Learned Dynamics

• Offline Reinforcement Learning with Conservative Q-Learning

  344UNOPENED

  Offline Reinforcement Learning with Conservative Q-Learning

• AI Safety via Adversarial Robustness

  345UNOPENED

  AI Safety via Adversarial Robustness

• Scalable Oversight with Recursive Reward Modeling

  346UNOPENED

  Scalable Oversight with Recursive Reward Modeling

• Evaluating Compositional Generalization with SCAN

  347UNOPENED

  Evaluating Compositional Generalization with SCAN

• Massive Multitask Language Understanding Benchmark (MMLU)

  348UNOPENED

  Massive Multitask Language Understanding Benchmark (MMLU)

• Probing Classifiers for Latent Concept Discovery

  349UNOPENED

  Probing Classifiers for Latent Concept Discovery

• Activation Quantization for Efficient Inference

  350UNOPENED

  Activation Quantization for Efficient Inference

• Structured Pruning with Lasso and Rewinding

  351UNOPENED

  Structured Pruning with Lasso and Rewinding

• Data Augmentation with Learned Semantic Transformations

  352UNOPENED

  Data Augmentation with Learned Semantic Transformations

• Data Valuation with the Data Shapley

  353UNOPENED

  Data Valuation with the Data Shapley

• The AI Winter and Its Causes

  354UNOPENED

  The AI Winter and Its Causes

• The ImageNet Moment and the Dawn of Deep Learning

  355UNOPENED

  The ImageNet Moment and the Dawn of Deep Learning

• Transformers with Linear Attention

  356UNOPENED

  Transformers with Linear Attention

• Training Dynamics of Large Language Models

  357UNOPENED

  Training Dynamics of Large Language Models

• Optimization for Non-Convex Landscapes with Entropy-SGD

  358UNOPENED

  Optimization for Non-Convex Landscapes with Entropy-SGD

• Universality and Approximation Theory of Neural Networks

  359UNOPENED

  Universality and Approximation Theory of Neural Networks

• PagedAttention for Efficient Memory Management in LLM Serving

  360UNOPENED

  PagedAttention for Efficient Memory Management in LLM Serving

• Generative Models for 3D-Aware Image Synthesis

  361UNOPENED

  Generative Models for 3D-Aware Image Synthesis

• Hierarchical Reinforcement Learning with Skills

  362UNOPENED

  Hierarchical Reinforcement Learning with Skills

• Anomaly Detection for AI Misalignment

  363UNOPENED

  Anomaly Detection for AI Misalignment

• Automated Circuit Discovery in Vision Transformers

  364UNOPENED

  Automated Circuit Discovery in Vision Transformers

• Dynamic Sparsity via RigL (Rigged Lottery)

  365UNOPENED

  Dynamic Sparsity via RigL (Rigged Lottery)