Article
Continuous batching from first principles
•
199
Jyot PRO
jeromepatel
·
AI & ML interests
None yet
Recent Activity
updated
a collection
1 day ago
Text to images
updated
a collection
1 day ago
Text to images
updated
a collection
1 day ago
Text to images
Organizations
upvoted
an
article
4 days ago
upvoted
3
articles
5 days ago
Article
SmolVLM2: Bringing Video Understanding to Every Device
•
315
Article
SmolVLM - small yet mighty Vision Language Model
•
386
Article
nanoVLM: The simplest repository to train your VLM in pure PyTorch
•
231
upvoted
an
article
6 days ago
Article
Mixture of Experts Explained
•
987
upvoted
a
paper
about 2 months ago
upvoted
a
collection
2 months ago
upvoted
an
article
3 months ago
Article
G2P Shrinks Speech Models
•
82
upvoted
a
collection
4 months ago
upvoted
7
papers
4 months ago
Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models
Paper
•
2410.10733
•
Published
•
8
Training Video Foundation Models with NVIDIA NeMo
Paper
•
2503.12964
•
Published
•
7
Qwen3 Technical Report
Paper
•
2505.09388
•
Published
•
317
HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels
Paper
•
2507.21809
•
Published
•
133
Stretching Each Dollar: Diffusion Training from Scratch on a Micro-Budget
Paper
•
2407.15811
•
Published
•
3
Mean Flows for One-step Generative Modeling
Paper
•
2505.13447
•
Published
•
7
Flow-GRPO: Training Flow Matching Models via Online RL
Paper
•
2505.05470
•
Published
•
86
upvoted
an
article
7 months ago
Article
You could have designed state of the art positional encoding
•
402
upvoted
a
paper
11 months ago