Rudrite Research — the frontier, made legible

Interactive, animated, visual explainers of landmark AI & ML papers — the systems and ideas behind the models you use, redrawn and made legible. Free and open.

Browse all 100 explainers · Guided reading tracks

• Attention Is All You Need
• FlashAttention
• PagedAttention (vLLM)
• Megatron-LM
• DeepSeek-R1
• GPT-3: Language Models are Few-Shot Learners
• ZeRO: Zero Redundancy Optimizer
• Mixtral of Experts
• Training Compute-Optimal Large Language Models
• Mamba: Linear-Time Sequence Modeling with Selective State Spaces
• BERT: Pre-training of Deep Bidirectional Transformers
• DeepSeek-V3
• Qwen3
• OLMo 2
• MiniMax-01
• Gemma 4
• Scaling Laws for Neural Language Models
• Adam: A Method for Stochastic Optimization
• Deep Residual Learning for Image Recognition
• Denoising Diffusion Probabilistic Models
• Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity
• LoRA: Low-Rank Adaptation of Large Language Models
• GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism
• GSPMD: General and Scalable Parallelization for ML Computation Graphs
• Pathways: Asynchronous Distributed Dataflow for ML
• Ring Attention with Blockwise Transformers for Near-Infinite Context
• Efficiently Scaling Transformer Inference
• Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving
• Fast Inference from Transformers via Speculative Decoding
• Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
• Training language models to follow instructions with human feedback
• Direct Preference Optimization: Your Language Model is Secretly a Reward Model
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
• Constitutional AI: Harmlessness from AI Feedback
• DAPO: An Open-Source LLM Reinforcement Learning System at Scale
• Tree of Thoughts: Deliberate Problem Solving with Large Language Models
• ReAct: Synergizing Reasoning and Acting in Language Models
• FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision
• Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
• DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
• EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty
• AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
• RoFormer: Enhanced Transformer with Rotary Position Embedding
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Learning Transferable Visual Models From Natural Language Supervision
• High-Resolution Image Synthesis with Latent Diffusion Models
• Scalable Diffusion Models with Transformers
• Robust Speech Recognition via Large-Scale Weak Supervision
• Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention
• Group Sequence Policy Optimization
• DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving
• CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion
• GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding
• GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints
• YaRN: Efficient Context Window Extension of Large Language Models
• Efficient Streaming Language Models with Attention Sinks
• Generative Adversarial Networks
• Segment Anything
• Visual Instruction Tuning
• s1: Simple test-time scaling
• Tülu 3: Pushing Frontiers in Open Language Model Post-Training
• Let's Verify Step by Step
• Self-Consistency Improves Chain of Thought Reasoning in Language Models
• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
• SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
• The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
• KAN: Kolmogorov–Arnold Networks
• Differential Transformer
• Mixture-of-Depths: Dynamically allocating compute in transformer-based language models
• RWKV: Reinventing RNNs for the Transformer Era
• Titans: Learning to Memorize at Test Time
• Byte Latent Transformer: Patches Scale Better Than Tokens
• The Llama 3 Herd of Models
• Mistral 7B
• Phi-4 Technical Report
• FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning
• Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
• Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
• Flow Matching for Generative Modeling
• Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty
• Rewarding Doubt: Calibrated Confidence Expression of LLMs
• Why Language Models Hallucinate
• τ-bench: Tool-Agent-User Interaction in Real-World Domains
• ToolRL: Reward is All Tool Learning Needs
• Group-in-Group Policy Optimization for LLM Agent Training
• MiniMax-M1: Scaling Test-Time Compute with Lightning Attention
• ProRL: Prolonged RL Expands Reasoning Boundaries
• The Entropy Mechanism of RL for Reasoning Language Models
• Spurious Rewards: Rethinking Training Signals in RLVR
• GenPRM: Generative Process Reward Models
• From Hard Refusals to Safe-Completions
• Proximal Policy Optimization Algorithms
• Efficiently Modeling Long Sequences with Structured State Spaces
• Auto-Encoding Variational Bayes
• Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
• Toolformer: Language Models Can Teach Themselves to Use Tools
• GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
• Muon is Scalable for LLM Training
• Consistency Models