Zhu Lin's picture

Zhu Lin

czl

·

https://czl.my/

AI & ML interests

Computer Vision, LLM

Recent Activity

updated a dataset about 19 hours ago

czl/nangang_sports_center

updated a dataset about 19 hours ago

czl/xinyi_public_gym

updated a dataset about 19 hours ago

czl/zhongshan_public_gym

View all activity

Organizations

upvoted a paper 23 days ago

Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference

Paper • 2412.13663 • Published Dec 18, 2024 • 163

upvoted an article 27 days ago

Article

Nemotron 3 Nano 4B: A Compact Hybrid Model for Efficient Local AI

27 days ago

•

62

upvoted a paper 29 days ago

Multimodal OCR: Parse Anything from Documents

Paper • 2603.13032 • Published Mar 13 • 43

upvoted an article about 2 months ago

Article

Forge: Scalable Agent RL Framework and Algorithm

Feb 13

•

146

upvoted 2 articles 4 months ago

Article

Aligning to What? Rethinking Agent Generalization in MiniMax M2

Oct 30, 2025

•

43

Article

What makes good reasoning data

Oct 30, 2025

•

44

upvoted 3 articles 5 months ago

Article

Building the Open Agent Ecosystem Together: Introducing OpenEnv

+8

Oct 23, 2025

•

159

Article

There is no such thing as a tokenizer-free lunch

Sep 25, 2025

•

95

Article

Evaluate Your Own RAG: Why Best Practices Failed Us

Nov 5, 2025

•

14

upvoted a paper 5 months ago

The Path Not Taken: RLVR Provably Learns Off the Principals

Paper • 2511.08567 • Published Nov 11, 2025 • 35

upvoted an article 6 months ago

Article

Why Did MiniMax M2 End Up as a Full Attention Model?

Oct 30, 2025

•

80

upvoted a collection 6 months ago

Nemotron-Pre-Training-Datasets

Large scale pre-training datasets used in the Nemotron family of models. • 12 items • Updated 8 days ago • 137

upvoted a paper 6 months ago

SSDD: Single-Step Diffusion Decoder for Efficient Image Tokenization

Paper • 2510.04961 • Published Oct 6, 2025 • 5

upvoted a collection 8 months ago

NVIDIA Nemotron V2

Open, Production-ready Enterprise Models. Nvidia Open Model license. • 9 items • Updated 8 days ago • 104

upvoted an article 8 months ago

Article

You could have designed state of the art positional encoding

Nov 25, 2024

•

464

upvoted a collection 8 months ago

Instruct datasets

5 items • Updated May 5, 2025 • 5

upvoted a collection 9 months ago

🧠 SmolLM3

Smol, multilingual, long-context reasoner • 14 items • Updated Oct 9, 2025 • 99

upvoted a collection 10 months ago

Gemma 3n

4 items • Updated Mar 12 • 270

upvoted a collection about 1 year ago

DeepSeek R1 (All Versions)

DeepSeek-R1-0528 is here! The most powerful reasoning open LLM, available in GGUF, original & 4-bit formats. Includes Llama & Qwen distilled models. • 37 items • Updated 10 days ago • 267

upvoted a paper over 1 year ago

Efficient Diffusion Models: A Comprehensive Survey from Principles to Practices

Paper • 2410.11795 • Published Oct 15, 2024 • 18