kuanweichen (Kuan-Wei Chen)

upvoted 2 articles 4 months ago

Article

You could have designed state of the art positional encoding

Nov 25, 2024

•

473

Article

The Optimal Architecture for Small Language Models

Dec 26, 2025

•

120

upvoted 2 papers 6 months ago

In-the-Flow Agentic System Optimization for Effective Planning and Tool Use

Paper • 2510.05592 • Published Oct 7, 2025 • 110

Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models

Paper • 2510.04618 • Published Oct 6, 2025 • 131

upvoted an article 10 months ago

Article

CodeAgents + Structure: A Better Way to Execute Actions

May 28, 2025

•

82

upvoted 4 articles about 1 year ago

Article

Training and Finetuning Reranker Models with Sentence Transformers

Mar 26, 2025

•

192

Article

Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth

Jul 29, 2024

•

370

Article

Uncensor any LLM with abliteration

Jun 13, 2024

•

845

Article

What is Qwen-Agent framework? Inside the Qwen family

Mar 20, 2025

•

13

upvoted a collection about 1 year ago

Qwen2.5

Collection

Qwen2.5 language models, including pretrained and instruction-tuned models of 7 sizes, including 0.5B, 1.5B, 3B, 7B, 14B, 32B, and 72B. • 43 items • Updated Mar 2 • 715

upvoted 4 articles about 1 year ago

Article

Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM

+2

Mar 12, 2025

•

495

Article

Introducing smolagents: simple agents that write actions in code.

+1

Dec 31, 2024

•

1.19k

Article

Open-R1: a fully open reproduction of DeepSeek-R1

+1

Jan 28, 2025

•

887

Article

Open-source DeepResearch – Freeing our search agents

+3

Feb 4, 2025

•

1.32k

upvoted an article over 1 year ago

Article

Introducing multi-backends (TRT-LLM, vLLM) support for Text Generation Inference

Jan 16, 2025

•

76

Kuan-Wei Chen

AI & ML interests

Organizations

You could have designed state of the art positional encoding

The Optimal Architecture for Small Language Models

In-the-Flow Agentic System Optimization for Effective Planning and Tool Use

Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models

CodeAgents + Structure: A Better Way to Execute Actions

Training and Finetuning Reranker Models with Sentence Transformers

Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth

Uncensor any LLM with abliteration

What is Qwen-Agent framework? Inside the Qwen family

Qwen2.5

Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM

Introducing smolagents: simple agents that write actions in code.

Open-R1: a fully open reproduction of DeepSeek-R1

Open-source DeepResearch – Freeing our search agents

Introducing multi-backends (TRT-LLM, vLLM) support for Text Generation Inference

Kuan-Wei Chen

AI & ML interests

Organizations

kuanweichen's activity

You could have designed state of the art positional encoding

The Optimal Architecture for Small Language Models

CodeAgents + Structure: A Better Way to Execute Actions

Training and Finetuning Reranker Models with Sentence Transformers

Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth

Uncensor any LLM with abliteration

What is Qwen-Agent framework? Inside the Qwen family

Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM

Introducing smolagents: simple agents that write actions in code.

Open-R1: a fully open reproduction of DeepSeek-R1

Open-source DeepResearch – Freeing our search agents

Introducing multi-backends (TRT-LLM, vLLM) support for Text Generation Inference