Machine Learning 37
- ViT: An Image Is Worth 16x16 Words
- NeRF: Representing Scenes as Neural Radiance Fields
- Articulate-Anything: Building Articulated 3D Assets with VLM Agents
- ROBOMETER: Scaling General-Purpose Robotic Reward Models
- TOPReward: Zero-Shot Robot Rewards from Token Probabilities
- Cosmos WFM (3/3): Applications — From Simulation to Reality
- Cosmos WFM (2/3): Training — Diffusion, Autoregressive, and Post-Training Recipes
- Cosmos WFM (1/3): Foundations — World Models, Data, and Tokenization
- Connecting Claude to Your Django REST API with MCP
- Why Should I Trust You? LIME Explained
- The Physics of Language Models
- Message Passing on Graphs: GCN and GAT
- Self-Supervised Learning for Computer Vision
- Learning to Learn: MAML and Prototypical Networks
- Direction in Noise
- 1000 Steps Back: The Math Behind DDPM
- Finding Signal in the Static
- The Paper That Started the Neural NLP Revolution: Bengio's Neural Probabilistic Language Model
- What If It Could Just Look It Up? RAG.
- ChapVidMR: Chapter-based Video Moment Retrieval
- Spitting the Details: The Tweaks That Made LLaMA
- Reading Both Ways: BERT and the End of Left-to-Right
- The Right Half: Decoder-Only Transformers
- FlashAttention
- Deja Vu, but Make It Linear: The KV Cache
- Where Do Facts Go to Live? MLPs, Superposition, and a Basketball Player Named Michael
- Attention Is a Third of What You Need: QKV, Dot Products, and the Other Two-Thirds
- Transformers: More Than Meets the Eye
- SIREN: Teaching Networks to Think in Sine Waves
- GANs: From a Thought Experiment to Photorealistic Faces
- When Neural Networks Lie: Adversarial Examples and the Art of Fooling AI
- From Autoencoders to VAEs: Learning to Generate, Not Just Compress
- LSTMs: How We Taught Neural Networks to Remember
- ML Normalization; A Primer
- ML Regularization; A Primer
- ML Optimization; A Primer
- Why CNNs Work: Histopathologic Cancer Detection