michal.i/o
- algorithms
- arrow
- bashrc x zshrc
- ClickHouse
- cloud
- Concurrency
- CRDTs
- cuda
- data visualization and dashboarding
- Databases
- django
- docker
- duckdb
- Engineering Blogs
- ffmpeg
- hardware
- Kafka
- kubernetes
- Latencies
- Leetcode
- logging
- networking
- object-stores
- parquet
- postgres
- python
- pytorch
- ray
- react-native
- redis
- rust
- search
- security
- sqlite
- terraform
- web-servers
- 2023-04-14 - Combined Scaling for Zero-shot Transfer Learning
- 2023-12-04 - MobileCLIP - Fast Image-Text Models through Multi-Modal Reinforced Training
- 2023-12-04 - Rejuvenating image-GPT as Strong Visual Representation Learners
- 2023-12-05 - Mamba Linear-Time Sequence Modeling with Selective State Spaces
- 2023-12-09 - SILC Improving Vision Language Pretraining with Self-Distillation
- 2023-12-09 - Text as Image Learning Transferable Adapter for Multi-Label Classification
- 2023-12-17 - Stable and low-precision training for large-scale vision-language models
- 2024-10-04 - Movie Gen A Cast of Media Foundation Models
- 2024-10-10 - Pixtral 12B
- 2024-11-03 - GATED DELTA NETWORKS IMPROVING MAMBA2 WITH DELTA RULE
- 2024-11-03 - On the Efficiency of Convolutional Neural Networks
- 2024-11-03 - ReMoE FULLY DIFFERENTIABLE MIXTURE-OF-EXPERTS WITH RELU ROUTING
- 2024-11-03 - TokenFormer - RETHINKING TRANSFORMER SCAL-ING WITH TOKENIZED MODEL PARAMETERS
- 2024-11-17 - Mixture-of-Transformers A Sparse and Scalable Architecture for Multi-Modal Foundation Models
- Bad apples for label noise early stopping
- Early Fusion Multimodal Encoder Models
- Latent Transformers with small vocabularies
- Learn to Initialize from OS Models
- Learning Skip Layers
- Mixture of Modules
- Multi Modal Learning to Rank as a replacement for CLIP
- Neural Architecture Search for SSM Hybrids
- Predict token from positional embedding
- Pretrain on synthetic conversation data
- Recurrent Computation with Transformers by repeating layers
- Remove all the things
- Sapiens for Robotics
- Small Proxy model to predict loss for given sample
- SSMs 4 Rec
- Task Routing for Multimodal LLMs
- Teach VLM to Zoom and Pan
- Tiny Foundational model by distilling from a lot of SOTA models
- Tiny LLMs with rag in the middle
- Two Stream SSMs
- Universal embedding space for popular foundational models (or adapters)
- Untitled
- VLMs for better Vision Backbones
- White space separated conv text encoder
- 3D Computer Vision
- A glossary of all the ways ML models fail to train
- Activation Functions
- Active Learning
- Agents
- Alignment and Post Training
- Approximate Nearest Neighbor Search (ANN)
- autograd
- benchmarks
- CLIP
- Cloud GPUs
- cnns
- Code LLMs
- compilers
- compression
- Computer Graphics
- Computer Vision Backbones
- Contrastive Learning
- Data Curation
- Data Formats for ML
- Data Loading
- Decoder Transformer Inference
- Decoding and Sampling
- Deep Learning Tricks of the Trade
- Deepspeed
- Diffusion Models
- Distributed Training
- Document Processing
- Embedding Models
- Evaluation Metrics
- Extreme Classification
- FairScale
- feature-stores
- Few Shot Learning
- fine-tuning
- Flow Matching - Rectified Flows
- Food Recognition
- Generative Models
- GPUs
- graphs
- Hallucinations
- Human Pose Estimation and Human Modeling
- Image Matching
- Image Recognition
- Imitation Learning
- Instance Recognition and Retrieval
- Instance Retrieval and Instance Recognition
- jax
- Label Noise
- Learning to Rank
- LLM Training and Tuning
- logsumexp
- Long Context Transformers
- Long Tail Classification and Class Imbalance
- Machine Learning Tricks and Best Practices
- maes
- Mamba
- matryoshka embeddings
- medical
- mixture of experts
- ML Competitions
- ML Conferences
- ML Courses & Books
- ML for Math
- ML Infrastructure
- ML Scaling
- MLX
- Mobile Inference
- Model Distillation and Transfer Learning
- Model Routing
- Multi Label Classification
- multi-modal
- multi-task
- Natural Language Processing
- nerf
- Networking
- Neural Architecture Search (NAS)
- Normalization
- Numerics
- Object Detection
- ocr
- paper-params
- Parameter Efficient Fine Tuning (PEFT)
- PrefixLM
- Pruning
- Quantization
- Recommendation Systems
- Reinforcement Learning (RL)
- resources
- Retrieval Augmented Generation (RAG)
- Retrieval Augmented Models
- RL for LMs
- Robotics
- segmentation
- Self-Supervised Image Models
- Semantic Search and Ranking
- Semi Supervised Learning
- Server Inference
- SLAM
- Small Foundational Models
- softmax
- speech
- Speedruns
- State Space Models (SSMs)
- Storage
- Structured Generation with LLMs
- Synthetic Data
- Tabular Machine Learning
- Tensor Tricks
- Test Time Compute and LLM Reasoning
- Text Embeddings
- text2sql
- Token Dropping, Pruning, Merging and Compression
- torch compile
- Transformer Alternatives (mostly SSMs)
- Transformer Properties
- transformers
- triton
- Untitled
- Variational Autoencoders (VAE)
- video
- Video Generation
- Vision Language Models
- Vision Transformers
- Visual Search
- xformers
- xlstm
- "World Models" - Modeling the Real World
- Autonomous Driving - Self Driving
- Function Calling (with LLMs)
- Mechanistic Interpretability
- C4AI Command R7B
- Conformer
- Contextual Document Embeddings (CDE)
- ControlNet
- DeltaNet
- DETR
- Diffusion Transformer (DiT)
- FLUX
- Gecko - Versatile Text Embeddings Distilled from Large Language Models
- HNSW
- InternVL
- Kolmogorov-Arnold Theorem
- KV Cache Compression
- Latent Diffusion
- LayerSkip
- LO-PQ
- Maximal Update Parametrization (μP)
- Mixture of Depth
- Mixture-of-Transformer
- MMDiT - Multi Modal Diffusion Transformer
- Not All Tokens Are What You Need For Pretraining
- PaliGemma
- Speech-to-Speech
- Stable Diffusion 3 and 3.5
- Test Time Learning (Local Learning)
- Token Dropping
- Tokenization
- Unified-IO
- Vision-Language-Action Models (VLA)
- Wav2vec
- WaveNet
- You Only Cache Once (YOCO)
- Untitled
- Untitled 1
Kafka
- algorithms
- arrow
- bashrc x zshrc
- ClickHouse
- cloud
- Concurrency
- CRDTs
- cuda
- data visualization and dashboarding
- Databases
- django
- docker
- duckdb
- Engineering Blogs
- ffmpeg
- hardware
- Kafka
- kubernetes
- Latencies
- Leetcode
- logging
- networking
- object-stores
- parquet
- postgres
- python
- pytorch
- ray
- react-native
- redis
- rust
- search
- security
- sqlite
- terraform
- web-servers
- 2023-04-14 - Combined Scaling for Zero-shot Transfer Learning
- 2023-12-04 - MobileCLIP - Fast Image-Text Models through Multi-Modal Reinforced Training
- 2023-12-04 - Rejuvenating image-GPT as Strong Visual Representation Learners
- 2023-12-05 - Mamba Linear-Time Sequence Modeling with Selective State Spaces
- 2023-12-09 - SILC Improving Vision Language Pretraining with Self-Distillation
- 2023-12-09 - Text as Image Learning Transferable Adapter for Multi-Label Classification
- 2023-12-17 - Stable and low-precision training for large-scale vision-language models
- 2024-10-04 - Movie Gen A Cast of Media Foundation Models
- 2024-10-10 - Pixtral 12B
- 2024-11-03 - GATED DELTA NETWORKS IMPROVING MAMBA2 WITH DELTA RULE
- 2024-11-03 - On the Efficiency of Convolutional Neural Networks
- 2024-11-03 - ReMoE FULLY DIFFERENTIABLE MIXTURE-OF-EXPERTS WITH RELU ROUTING
- 2024-11-03 - TokenFormer - RETHINKING TRANSFORMER SCAL-ING WITH TOKENIZED MODEL PARAMETERS
- 2024-11-17 - Mixture-of-Transformers A Sparse and Scalable Architecture for Multi-Modal Foundation Models
- Bad apples for label noise early stopping
- Early Fusion Multimodal Encoder Models
- Latent Transformers with small vocabularies
- Learn to Initialize from OS Models
- Learning Skip Layers
- Mixture of Modules
- Multi Modal Learning to Rank as a replacement for CLIP
- Neural Architecture Search for SSM Hybrids
- Predict token from positional embedding
- Pretrain on synthetic conversation data
- Recurrent Computation with Transformers by repeating layers
- Remove all the things
- Sapiens for Robotics
- Small Proxy model to predict loss for given sample
- SSMs 4 Rec
- Task Routing for Multimodal LLMs
- Teach VLM to Zoom and Pan
- Tiny Foundational model by distilling from a lot of SOTA models
- Tiny LLMs with rag in the middle
- Two Stream SSMs
- Universal embedding space for popular foundational models (or adapters)
- Untitled
- VLMs for better Vision Backbones
- White space separated conv text encoder
- 3D Computer Vision
- A glossary of all the ways ML models fail to train
- Activation Functions
- Active Learning
- Agents
- Alignment and Post Training
- Approximate Nearest Neighbor Search (ANN)
- autograd
- benchmarks
- CLIP
- Cloud GPUs
- cnns
- Code LLMs
- compilers
- compression
- Computer Graphics
- Computer Vision Backbones
- Contrastive Learning
- Data Curation
- Data Formats for ML
- Data Loading
- Decoder Transformer Inference
- Decoding and Sampling
- Deep Learning Tricks of the Trade
- Deepspeed
- Diffusion Models
- Distributed Training
- Document Processing
- Embedding Models
- Evaluation Metrics
- Extreme Classification
- FairScale
- feature-stores
- Few Shot Learning
- fine-tuning
- Flow Matching - Rectified Flows
- Food Recognition
- Generative Models
- GPUs
- graphs
- Hallucinations
- Human Pose Estimation and Human Modeling
- Image Matching
- Image Recognition
- Imitation Learning
- Instance Recognition and Retrieval
- Instance Retrieval and Instance Recognition
- jax
- Label Noise
- Learning to Rank
- LLM Training and Tuning
- logsumexp
- Long Context Transformers
- Long Tail Classification and Class Imbalance
- Machine Learning Tricks and Best Practices
- maes
- Mamba
- matryoshka embeddings
- medical
- mixture of experts
- ML Competitions
- ML Conferences
- ML Courses & Books
- ML for Math
- ML Infrastructure
- ML Scaling
- MLX
- Mobile Inference
- Model Distillation and Transfer Learning
- Model Routing
- Multi Label Classification
- multi-modal
- multi-task
- Natural Language Processing
- nerf
- Networking
- Neural Architecture Search (NAS)
- Normalization
- Numerics
- Object Detection
- ocr
- paper-params
- Parameter Efficient Fine Tuning (PEFT)
- PrefixLM
- Pruning
- Quantization
- Recommendation Systems
- Reinforcement Learning (RL)
- resources
- Retrieval Augmented Generation (RAG)
- Retrieval Augmented Models
- RL for LMs
- Robotics
- segmentation
- Self-Supervised Image Models
- Semantic Search and Ranking
- Semi Supervised Learning
- Server Inference
- SLAM
- Small Foundational Models
- softmax
- speech
- Speedruns
- State Space Models (SSMs)
- Storage
- Structured Generation with LLMs
- Synthetic Data
- Tabular Machine Learning
- Tensor Tricks
- Test Time Compute and LLM Reasoning
- Text Embeddings
- text2sql
- Token Dropping, Pruning, Merging and Compression
- torch compile
- Transformer Alternatives (mostly SSMs)
- Transformer Properties
- transformers
- triton
- Untitled
- Variational Autoencoders (VAE)
- video
- Video Generation
- Vision Language Models
- Vision Transformers
- Visual Search
- xformers
- xlstm
- "World Models" - Modeling the Real World
- Autonomous Driving - Self Driving
- Function Calling (with LLMs)
- Mechanistic Interpretability
- C4AI Command R7B
- Conformer
- Contextual Document Embeddings (CDE)
- ControlNet
- DeltaNet
- DETR
- Diffusion Transformer (DiT)
- FLUX
- Gecko - Versatile Text Embeddings Distilled from Large Language Models
- HNSW
- InternVL
- Kolmogorov-Arnold Theorem
- KV Cache Compression
- Latent Diffusion
- LayerSkip
- LO-PQ
- Maximal Update Parametrization (μP)
- Mixture of Depth
- Mixture-of-Transformer
- MMDiT - Multi Modal Diffusion Transformer
- Not All Tokens Are What You Need For Pretraining
- PaliGemma
- Speech-to-Speech
- Stable Diffusion 3 and 3.5
- Test Time Learning (Local Learning)
- Token Dropping
- Tokenization
- Unified-IO
- Vision-Language-Action Models (VLA)
- Wav2vec
- WaveNet
- You Only Cache Once (YOCO)
- Untitled
- Untitled 1
Backlinks
- No backlinks found