michal.i/o
Search
Search
Dark mode
Light mode
Explorer
blog
2022-12-17 TIL
Excalidraw
Drawing 2024-10-23 21.07.26.excalidraw
Drawing 2024-10-24 09.42.53.excalidraw
Drawing 2024-10-24 12.30.58.excalidraw
Drawing 2024-10-26 09.48.03.excalidraw
Drawing 2024-11-03 16.11.48.excalidraw
journal
2024-08-12
2024-08-19
2024-08-26
2024-09-02
2024-09-09
2024-09-16
2024-09-18 - Pytorch Conference Notes
2024-09-23
2024-09-30
2024-10-07
2024-10-14
2024-10-21
2024-10-28
2024-11-04
2024-11-18
notes
business
accounting
consulting
Growth
legal
marketing
Open Source Business Models
pricing
Productivity Software
sales
VC Alternatives
dev
algorithms
arrow
bashrc x zshrc
ClickHouse
cloud
CRDTs
cuda
data visualization and dashboarding
Databases
django
docker
duckdb
ffmpeg
hardware
kubernetes
Latencies
logging
networking
object-stores
parquet
postgres
python
pytorch
ray
react-native
redis
rust
search
security
sqlite
terraform
web-servers
math
Linear Algebra
Math for ML
Optimization
Probability
ml
conferences
2023 NeurIPS
models
Mistral7B
papers
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
research ideas
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
Multi Modal Learning to Rank as a replacement for CLIP
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
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
A glossary of all the ways ML models fail to train
Active Learning
Alignment and Post Training
Approximate Nearest Neighbor Search
autograd
benchmarks
CLIP
Cloud GPUs
cnns
Code LLMs
compilers
compression
Computer Graphics
Computer Vision Backbones
contrastive
Data Formats for ML
Data Loading
datasets
Decoder Transformer Inference
Deepspeed
detection
Diffusion Models
distill
Distributed Training
Embedding Models
Evaluation Metrics
Extreme Classification
FairScale
feature-stores
Few Shot Learning
fine-tuning
Flow Matching
GPUs
graphs
Human Pose Estimation and Human Modeling
Image Generation
Image Recognition
Imitation Learning
Instance Recognition and Retrieval
Instance Retrieval and Instance Recognition
jax
Label Noise
Learning to Rank
LLM Reasoning and Test Time Compute
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 Conferences
ML for Math
ML Infrastructure
ML Scaling
MLX
Mobile Inference
Model Routing
Multi Label Classification
multi-modal
multi-task
Natural Language Processing
nerf
Networking
Normalization
Numerics
ocr
paper-params
Parameter Efficient Fine Tuning (PEFT)
PrefixLM
Quantization
recommenders
resources
Retrieval Augmented Generation (RAG)
Retrieval Augmented Models
rl
RL for LMs
Robotics
segmentation
semantic-search
semisup
Server Inference
SLAM
Small Foundational Models
softmax
speech
State Space Models (SSMs)
Storage
Synthetic Data
Tabular Machine Learning
Tensor Tricks
Text Embeddings
text2sql
torch compile
Transformer Alternatives (mostly SSMs)
Transformer Properties
transformers
tricks
triton
video
Video Generation
Vision - Language Models
Vision Transformers
Visual Search
xformers
xlstm
Home
❯
notes
❯
ml
Folder: notes/ml
110 items under this folder.
Nov 20, 2024
Natural Language Processing
Nov 20, 2024
Multi Label Classification
Nov 20, 2024
Model Routing
routing
Nov 20, 2024
Mobile Inference
ml/mobile
Nov 20, 2024
Mamba
ssm
Nov 20, 2024
Machine Learning Tricks and Best Practices
Nov 20, 2024
MLX
mlx
Nov 20, 2024
ML for Math
Nov 20, 2024
ML Scaling
Nov 20, 2024
ML Infrastructure
ml/ops
Nov 20, 2024
ML Conferences
Nov 20, 2024
Long Tail Classification and Class Imbalance
Nov 20, 2024
Long Context Transformers
transformers
Nov 20, 2024
Learning to Rank
Nov 20, 2024
Label Noise
Nov 20, 2024
LLM Training and Tuning
Nov 20, 2024
LLM Reasoning and Test Time Compute
Nov 20, 2024
Instance Retrieval and Instance Recognition
Nov 20, 2024
Instance Recognition and Retrieval
Nov 20, 2024
Imitation Learning
Nov 20, 2024
Image Recognition
Nov 20, 2024
Image Generation
Nov 20, 2024
Human Pose Estimation and Human Modeling
Nov 20, 2024
GPUs
gpu
hardware
Nov 20, 2024
Flow Matching
Nov 20, 2024
Few Shot Learning
Nov 20, 2024
FairScale
Nov 20, 2024
Extreme Classification
Nov 20, 2024
Evaluation Metrics
Nov 20, 2024
Embedding Models
text-embeddings
Nov 20, 2024
Distributed Training
distributed
Nov 20, 2024
Diffusion Models
Nov 20, 2024
Deepspeed
Nov 20, 2024
Decoder Transformer Inference
inference
llm
Nov 20, 2024
Data Loading
Nov 20, 2024
Data Formats for ML
Nov 20, 2024
Computer Vision Backbones
cv
Nov 20, 2024
Computer Graphics
Nov 20, 2024
Code LLMs
Nov 20, 2024
Cloud GPUs
Nov 20, 2024
CLIP
clip
vision-language
contrastive
multimodal
Nov 20, 2024
Approximate Nearest Neighbor Search
Nov 20, 2024
Alignment and Post Training
Nov 20, 2024
Active Learning
Nov 20, 2024
A glossary of all the ways ML models fail to train
Nov 20, 2024
3d
Nov 20, 2024
xlstm
Nov 20, 2024
xformers
Nov 20, 2024
video
Nov 20, 2024
triton
Nov 20, 2024
tricks
Nov 20, 2024
transformers
ml/nlp/llm
Nov 20, 2024
torch compile
Nov 20, 2024
text2sql
Nov 20, 2024
speech
asr
Nov 20, 2024
softmax
Nov 20, 2024
semisup
Nov 20, 2024
semantic-search
retrieval
word-embeddings
bert
colbert
search
crossencoders
Nov 20, 2024
segmentation
Nov 20, 2024
rl
Nov 20, 2024
resources
Nov 20, 2024
recommenders
Nov 20, 2024
paper-params
Nov 20, 2024
ocr
Nov 20, 2024
nerf
Nov 20, 2024
multi-task
Nov 20, 2024
multi-modal
Nov 20, 2024
mixture of experts
moe
Nov 20, 2024
medical
ml/applied/med
Nov 20, 2024
matryoshka embeddings
Nov 20, 2024
maes
Nov 20, 2024
logsumexp
Nov 20, 2024
jax
Nov 20, 2024
graphs
Nov 20, 2024
fine-tuning
Nov 20, 2024
feature-stores
Nov 20, 2024
distill
Nov 20, 2024
detection
Nov 20, 2024
datasets
Nov 20, 2024
contrastive
Nov 20, 2024
compression
Nov 20, 2024
compilers
Nov 20, 2024
cnns
Nov 20, 2024
benchmarks
Nov 20, 2024
autograd
Nov 20, 2024
Visual Search
Nov 20, 2024
Vision Transformers
Nov 20, 2024
Vision - Language Models
Nov 20, 2024
Video Generation
Nov 20, 2024
Transformer Properties
Nov 20, 2024
Transformer Alternatives (mostly SSMs)
Nov 20, 2024
Text Embeddings
Nov 20, 2024
Tensor Tricks
pytorch
Nov 20, 2024
Tabular Machine Learning
Nov 20, 2024
Synthetic Data
Nov 20, 2024
Storage
Nov 20, 2024
State Space Models (SSMs)
ssm
mamba
Nov 20, 2024
Small Foundational Models
Nov 20, 2024
Server Inference
Nov 20, 2024
SLAM
Nov 20, 2024
Robotics
Nov 20, 2024
Retrieval Augmented Models
Nov 20, 2024
Retrieval Augmented Generation (RAG)
Nov 20, 2024
RL for LMs
rl
Nov 20, 2024
Quantization
Nov 20, 2024
PrefixLM
Nov 20, 2024
Parameter Efficient Fine Tuning (PEFT)
peft
Nov 20, 2024
Numerics
Nov 20, 2024
Normalization
Nov 20, 2024
Networking