📝 Notes
Search
Search
Search
Dark mode
Light mode
Explorer
Advance Energy Systems
control rods
Dyson Spheres
Fission Reaction
gaseous diffusion
moderator
Neutron Scattering
Nuclear Power Plants
Nuclear Reactor
The Grid
uranium enrichment
Biology
The Genetic Code
Computer Architecture
AC
ARM architecture
CMOS
Compute-in-Memory (CIM)
Computer Architecture
inverter
NMOS
Parallel Processors
PMOS
Computer Vision
Slam
Cryptography
Cryptography
Mono-alphabetic substition
STARKs
The Vigenère (poly-alphabetic shift) cipher
CUDA
3-component vector that represent the thread index within a block 1
CUDA
Data Structures and Algos
KD Tree
Economics
Wealth of Nations
Education
Large Model Systems
1 bit LLMs
Allreduce
CLIP
CUDA API of GPT 2
Deep Dive of GPT architecture
Gemini
How a Transformer works at inference vs training time
IEEE-754
Liger Kernels
LlaMa from scratch
LLaVA
MatMul-Free Language Modeling
ML Interpretability
Optical Circuit Switches
Positional embeddings matrix
Post-Training Static quantization
Quantization
queries (Q), keys (K), and values (V)
Silent Data Corruption (SDC)
Softmax
SparseCore
SSM vs Transformer
Token embeddings matrix
Tokenization
Torchserve
TPUv4
Training GPT from Scratch
Transformers
Vector-matrix multiplication (VMM)
VIdeo understanding
Vision Transformer
Linux Kernel Development
linux_kernel_development
Memory
Memory
MRI
Political Theory
Political Theory
Psychology
Developmental Psychology
Erickson
Piaget
Vygotsky
Religion
Bible
Genesis
Genesis
Genesis 1-2
Genesis 3
Genesis 4-5
Genesis 6-9
Genesis 10-11
Genesis 12-25
Genesis 26-27
Genesis 28-36
Genesis 37-50
Bible
Screenplay Writing
Screenplay Course
Verilog
learning_verilog
Content Feed
Home
❯
Large Model Systems
❯
VIdeo understanding
VIdeo understanding
Nov 06, 2025
1 min read
accomplished by encoding the video as a sequence of frames in the large context window.
Graph View
Backlinks
No backlinks found