Leo PRO

leideng

·

https://leideng.github.io/

AI & ML interests

Efficient AI, Sparse Attention

Recent Activity

liked a model about 22 hours ago

Qwen/Qwen2.5-VL-7B-Instruct-AWQ

liked a model about 22 hours ago

hfl/Qwen2.5-VL-7B-Instruct-GPTQ-Int4

liked a dataset 2 days ago

Lin-Chen/MMStar

View all activity

Organizations

None yet

upvoted a paper about 2 months ago

FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention

Paper • 2606.09079 • Published Jun 8 • 69

upvoted a paper 2 months ago

Are We Ready For An Agent-Native Memory System?

Paper • 2606.24775 • Published Jun 23 • 138

upvoted a paper 3 months ago

KV Packet: Recomputation-Free Context-Independent KV Caching for LLMs

Paper • 2604.13226 • Published Apr 14 • 11

upvoted a paper 4 months ago

Generative Recursive Reasoning

Paper • 2605.19376 • Published May 20 • 31

upvoted 2 articles 4 months ago

Article

Unlocking Agentic RL Training for GPT-OSS: A Practical Retrospective

LinkedIn

•

Jan 27

• 82

Article

Nanochat-Ascend: Training Karpathy's Nanochat on Ascend NPU (Part 1)

leideng

•

Jun 6

• 1

upvoted a paper 4 months ago

On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification

Paper • 2508.05629 • Published Aug 7, 2025 • 191

upvoted an article 4 months ago

Article

TRL v1.0: Post-Training Library Built to Move with the Field

+2

qgallouedec, stevhliu, pcuenq, sergiopaniego

•

Mar 31

• 60

upvoted a collection 5 months ago

Open Coding Agents

13 items • Updated Mar 5 • 56

upvoted an article 6 months ago

Article

Fine-Tuning Your First Large Language Model (LLM) with PyTorch and Hugging Face

dvgodoy

•

Feb 11, 2025

• 130

upvoted 2 collections 6 months ago

Gemma 4

Our most intelligent open models to date • 16 items • Updated Aug 20 • 1.15k

Transformers.js V4 demos

A collection of demos built with Transformers.js V4 • 24 items • Updated Apr 16 • 73

upvoted 2 papers 6 months ago

FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language

Paper • 2506.20920 • Published Jun 26, 2025 • 80

The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale

Paper • 2406.17557 • Published Jun 25, 2024 • 106

upvoted 2 collections 6 months ago

Qwen3.5

21 items • Updated Mar 9 • 1.79k

Olmo Hybrid

6 items • Updated Mar 5 • 28

upvoted a collection 8 months ago

NVIDIA Nemotron v3

Open, Production-ready Enterprise Models • 33 items • Updated Aug 14 • 378

upvoted an article 8 months ago

Article

~Don't~ Repeat Yourself

patrickvonplaten

•

Apr 5, 2022

• 56

upvoted a collection over 1 year ago

SmolLM2

State-of-the-art compact LLMs for on-device applications: 1.7B, 360M, 135M • 16 items • Updated May 5, 2025 • 314