-
Improved Denoising Diffusion Probabilistic Models (iDDPM)
-
Diffusion notes
-
Common Diffusion Noise Schedules and Sample Steps are Flawed
-
Denoising Diffusion Probabilistic Models (DDPM)
-
RL fundamentals
-
PPO - phase 1
-
some heuristics
-
RoPE notes
-
Reinforcement Learning Notes
-
Reward Models
-
ORM & PRM Validation-Split Runs
-
KL divergence notes
-
oss pr#1 - luminal/example-bert example worklog
-
ML basics notes
-
Information Retrieval notes
-
word2vec notes
-
webrtc notes
-
SegMamba notes
-
Mamba in vision, seen as linear attention (MLLA)
-
Hungry Hungry Hippos (H3) notes
-
S4 notes
-
Kalman filter notes
-
Mamba notes
-
The matrix calculus you need for deep learning
-
HiPPO notes
-
Transformers notes
-
SSM notes
-
Bahdanau attention notes
-
Segment Anything notes
-
U-Net notes
-
FCN notes
-
BERT notes
-
Viola-Jones notes
-
geohash notes