Article
Understanding Vector Quantization in VQ-VAE
ariG23498
• • 64Austin Liu
Austin362667
AI & ML interests
None yet
Recent Activity
upvoted an article 19 days ago
Understanding Vector Quantization in VQ-VAE upvoted an article about 1 month ago
Pallas for people who know JAX but not kernels yet updated a dataset about 1 month ago
Austin362667/fineweb10B_sp8192Organizations
upvoted an article 19 days ago
upvoted an article about 1 month ago
Article
Pallas for people who know JAX but not kernels yet
ariG23498
• • 21 upvoted an article about 2 months ago
Article
The PR you would have opened yourself
pcuenq, awni
• • 72 upvoted a paper 2 months ago
upvoted 2
articles 3 months ago
Article
Assisted Generation: a new direction toward low-latency text generation
joaogante
• • 79 Article
A Gentle Introduction to 8-bit Matrix Multiplication for transformers at scale using transformers, accelerate and bitsandbytes
ybelkada, timdettmers
• • 134 upvoted a collection 3 months ago
upvoted 3
articles 4 months ago
Article
OpenEvolve: An Open Source Implementation of Google DeepMind's AlphaEvolve
codelion
• • 69 Article
KV Cache from scratch in nanoVLM
- +3
ariG23498, kashif, lusxvr, andito, pcuenq
• • 120 Article
Unlocking Agentic RL Training for GPT-OSS: A Practical Retrospective
LinkedIn
• • 77 upvoted an article 6 months ago
Article
Continuous batching from first principles
- +1
ror, ArthurZ, mcpotato
• • 403 upvoted 2
articles 8 months ago
Article
Key Insights into the Law of Vision Representations in MLLMs
Borise
• • 20 Article
KV Caching Explained: Optimizing Transformer Inference Efficiency
not-lain
• • 344 upvoted 6
articles 11 months ago
Article
An Analysis of Chinese LLM Censorship and Bias with Qwen 2 Instruct
leonardlin
• • 69 Article
Parquet Content-Defined Chunking
kszucs
• • 75 Article
SmolVLA: Efficient Vision-Language-Action Model trained on Lerobot Community Data
- +7
danaaubakirova, andito, merve, ariG23498, fracapuano, loubnabnl, pcuenq, mshukor, cadene
• • 351 Article
TimeScope: How Long Can Your Video Large Multimodal Model Go?
- +2
orrzohar, ruili0, andito, nicholswang
• • 48 Article
⚡ nano-vLLM: Lightweight, Low-Latency LLM Inference from Scratch
zamal
• • 44 Article
SmolVLM2: Bringing Video Understanding to Every Device
- +5
orrzohar, mfarre, andito, merve, pcuenq, cyrilzakka, Xenova
• • 340 upvoted an article 12 months ago
Article
Introducing Cosmos Predict-2: A Foundation For Your Own World Model
nvidia
• • 9