Open to Work

7 25 38

Zixi "Oz" Li PRO

OzTianlu

https://github.com/lizixi-0x2F

lizixi-0x2F

AI & ML interests

My research focuses on deep reasoning with small language models, Transformer architecture innovation, and knowledge distillation for efficient alignment and transfer.

Recent Activity

updated a model about 3 hours ago

NoesisLab/Collins-Embedding-3M

liked a model about 4 hours ago

mispeech/dashengtokenizer

liked a model 1 day ago

NoesisLab/Kai-3B-Distill-Claude-Opus-4.5

View all activity

Organizations

upvoted a paper 7 days ago

CodeScaler: Scaling Code LLM Training and Test-Time Inference via Execution-Free Reward Models

Paper • 2602.17684 • Published Feb 4 • 22

upvoted a paper 8 days ago

Efficient RLVR Training via Weighted Mutual Information Data Selection

Paper • 2603.01907 • Published 10 days ago • 14

upvoted a paper 9 days ago

Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning

Paper • 2504.13914 • Published Apr 10, 2025 • 5

upvoted a collection 9 days ago

Seed Flagship Model Released

Collection

contributed • 7 items • Updated 9 days ago • 3

upvoted a paper 11 days ago

DualPath: Breaking the Storage Bandwidth Bottleneck in Agentic LLM Inference

Paper • 2602.21548 • Published 15 days ago • 43

upvoted an article 11 days ago

Article

Exploring New Frontiers of LLMs: Adaptive Dual-Search Distillation (ADS) and the 30B Model Open Beta

11 days ago

•

upvoted an article 14 days ago

Article

GGML and llama.cpp join HF to ensure the long-term progress of Local AI

20 days ago

•

481

upvoted a collection 14 days ago

Kai Models Series

Collection

Kai Models Distilled via Adaptive Dual Search Distillation • 3 items • Updated 10 days ago • 2

upvoted a paper 14 days ago

Nacrith: Neural Lossless Compression via Ensemble Context Modeling and High-Precision CDF Coding

Paper • 2602.19626 • Published 17 days ago • 3

upvoted an article 15 days ago

Article

Shattering the Memory Wall: O(1) Inference and Causal Monoid State Compression in Spartacus-1B

15 days ago

•

upvoted a collection 22 days ago

Spartacus Monoid Reasoning Models

Collection

O(1) Reasoning Models • 1 item • Updated 15 days ago • 2

upvoted an article about 1 month ago

Article

The Optimal Architecture for Small Language Models

Dec 26, 2025

•

119

upvoted a collection about 1 month ago

Geilim Smol Language Models

Collection

Geilim Smol Language Models • 2 items • Updated 9 days ago • 1

upvoted 2 papers about 2 months ago

Trainable Dynamic Mask Sparse Attention

Paper • 2508.02124 • Published Aug 4, 2025 • 19

Reasoning: From Reflection to Solution

Paper • 2511.11712 • Published Nov 12, 2025 • 2

upvoted a paper 3 months ago

Weight-sparse transformers have interpretable circuits

Paper • 2511.13653 • Published Nov 17, 2025 • 2

upvoted a collection 4 months ago

Reasoning at the Edge (HF Preprints)

Collection

This collection traces the mathematical and empirical limits of machine reasoning. • 12 items • Updated 12 days ago • 1

upvoted a collection 5 months ago

🐕Small-Doges

Collection

Doge family of small language models! • 18 items • Updated Apr 21, 2025 • 11

upvoted an article 6 months ago

Article

Project SmolMoE-8x135M: From Zero to a Custom Mixture-of-Experts Model

Aug 7, 2025

•

upvoted an article 7 months ago

Article

别让显存扼杀你的AI梦！我的“魔改”Gemma实战，从模型“瘦身”到中文“重生”

Aug 1, 2025

•

Zixi "Oz" Li PRO

AI & ML interests

Recent Activity

Organizations

OzTianlu's activity

Exploring New Frontiers of LLMs: Adaptive Dual-Search Distillation (ADS) and the 30B Model Open Beta

GGML and llama.cpp join HF to ensure the long-term progress of Local AI

Shattering the Memory Wall: O(1) Inference and Causal Monoid State Compression in Spartacus-1B

The Optimal Architecture for Small Language Models

Project SmolMoE-8x135M: From Zero to a Custom Mixture-of-Experts Model

别让显存扼杀你的AI梦！我的“魔改”Gemma实战，从模型“瘦身”到中文“重生”