10:53

10-minute paper (episode 33): Ferret-v2: An Improved Baseline for Referring and Grounding with LLM

16:08

10-minute paper (episode 32): A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts

21:50

10-minute paper (episode 31): Self-Supervised Learning from Images I-JEPA

13:17

Mojo - First impression

25:05

10-minute paper (episode 30): ColT5 (Part 1): Faster, Long-Range Transformers

31:08

10 minutes paper (episode 29): Table Extraction

27:25

10 minutes paper (episode 28): AliBi; Train Short, Test Long

25:34

Ray (Episode 4): Deploying 7B GPT using Ray

26:39

Ray (Episode 3): Memory management in Ray Object Store

49:20

Ray (Episode 2): Actor models

20:52

Ray (Episode 1): Remote function

39:23

10 minutes paper (episode 27): LLM powered autonomous agents

30:06

10 minutes paper (episode 26):Multi-Grained Vision Language Pre-Training: X-VLM

21:35

10 minutes paper (episode 25): Low Rank Adaptation: LoRA

20:00

AI-Code-Mastery (Episode 8): Fine-Tuning MPT-7B by Single GPU | Open-Source and Commercializable

13:54

10 minutes paper (episode 24): ViperGPT

23:32

10 minutes paper (episode 23): Unlocking Full Potential of Language Models with Chain-of-Thought

25:57

AI-Code-Mastery (Episode 7): Text2Image using Diffusion Model and ControlNet

09:31

AI-Code-Mastery (Episode 6): Explore the Best ML Challenge Websites and Datasets

34:58

AI-Code-Mastery (Episode 5): Zero-Shot document question answering with Flan-ULv2

59:34

AI-Code-Mastery (Episode 4): Torch Drug

29:43

10 minutes paper (episode 22); Beyond neural scaling laws

34:31

10 minutes paper (episode 21); LayoutReader

26:28

10 minutes paper (episode 20); InstructGPT

47:53

AI-Code-Mastery (Episode 3): Split

01:09:59

AI-Code-Mastery (Episode 2): alert, diffdir, conv, ocr

36:13

AI-Code-Mastery (Episode 1): Cython

20:12

10 minutes paper (episode 19); ConvNeXt: A ConvNet for the 2020s

18:33

10 minutes paper (episode 18); Similarity of Neural Network Representations Revisited

08:30

10 minutes paper (episode 17); Micro-Batch Training

01:53:52

Implement U-Net (PyTorch)

01:32:37

Training your first image classifier (Pytorch)

01:45:07

Model Training and Evaluation (Pytorch)

14:27

10 minutes paper (episode 16); Zero-Shot Text-to-Image Generation

13:06

10 minutes paper (episode 15); Multi-Task Self-Training for Learning General Representations

08:07

10 minutes paper (episode 14); A Data-Augmentation Is Worth A Thousand Samples

09:38

10 minutes paper (episode 13); Sample size determination

14:17

10 minutes paper (episode 12); Graph Attention Network

18:19

10 minutes paper (episode 11); Electra: Pre-training Text Encoders as Discriminators

17:53

10 minutes paper (episode 10); Involution

22:01

10 minutes paper (episode 9); Tabular data processing

22:58

10 minutes paper (episode 8); Learning from Demonstration.

19:46

10 minutes paper (episode 7); Displaced Aggregation Unit; is a replacement for classical convnet?

11:45

10 minutes paper (episode 6); Transparent Reporting for Prognosis Or Diagnosis

23:44

10 minutes paper (episode 5); Proximal Policy Optimization Algorithms

14:26

10 minutes paper (episode 4); Spiking NN

13:40

10 minutes paper (episode 3); Bootstrap your own latent.

14:50

10 minutes paper (episode 2); Offline knowledge distillation.

11:13

10 minutes paper (episode 1); On the Dark Side of Calibration for Modern Neural Networks

21:22

Probability Calibration for Classification (Platt, isotonic, logistic and beta)

43:09

Node Classification using Graph Convolutional Networks

01:12:27

WaveNet (Theory and Implementation)

46:14

Pandas (Beginner to advanced)

55:27

Numpy (Beginner to Advanced)

36:37

Transformers (Implementation)

34:34

Attention is all you need (implementation)