58 539

Huu-Hiep Nguyen

hiepnh

AI & ML interests

None yet

Recent Activity

upvoted an article about 22 hours ago

Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries

upvoted an article about 22 hours ago

Streaming datasets: 100x More Efficient

liked a model 2 days ago

Qwen/Qwen3-Coder-Next

View all activity

Organizations

upvoted 2 articles about 22 hours ago

Article

Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries

3 days ago

•

Article

Streaming datasets: 100x More Efficient

Oct 27, 2025

•

upvoted an article 3 days ago

Article

From Golden Gate Bridge to Broken JSON: Why Anthropic's SAE Steering Fails for Structured Output

Feb 7

•

upvoted a paper 3 days ago

OpenMed NER: Open-Source, Domain-Adapted State-of-the-Art Transformers for Biomedical NER Across 12 Public Datasets

Paper • 2508.01630 • Published Aug 3, 2025 • 15

upvoted 3 articles 3 days ago

Article

Unlocking Healthcare AI: I'm Releasing State-of-the-Art Medical Models for Free. Forever.

Jul 16, 2025

•

154

Article

OpenMed: Six Months of Open-Source Medical AI and the Road Ahead

Jan 6

•

Article

The ML Engineer's Guide to Protein AI

9 days ago

•

upvoted an article 7 days ago

Article

NEO-unify: Building Native Multimodal Unified Models End to End

7 days ago

•

upvoted 3 articles 9 days ago

Article

Visual Aesthetic Benchmark: Can Frontier Models Judge Beauty?

16 days ago

•

Article

Create, Evaluate, and Connect AI Skills | SkillNet: A Large-Scale Agentic "Skill Graph" Knowledge Base

13 days ago

•

Article

From GRPO to DAPO and GSPO: What, Why, and How

Aug 9, 2025

•

100

upvoted an article 14 days ago

Article

Mixture of Experts (MoEs) in Transformers

15 days ago

•

130

upvoted an article 16 days ago

Article

FINAL Bench: The Real Bottleneck to AGI Is Self-Correction

20 days ago

•

upvoted 4 articles about 1 month ago

Article

We Got Claude to Build CUDA Kernels and teach open models!

Jan 28

•

149

Article

Slashing torch.compile Warmup & LoRA Swapping Times with Pruna

Jan 28

•

Article

Tokenization in Transformers v5: Simpler, Clearer, and More Modular

Dec 18, 2025

•

122

Article

The Great Classification Showdown: OSS vs BERT on Consumer Hardware

Jan 26

•

upvoted 2 articles about 2 months ago

Article

LightOnOCR-2-1B: a lightweight high-performance end-to-end OCR model family

Jan 19

•

Article

Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment

Feb 11, 2025

•

110

upvoted an article 2 months ago

Article

Encoding the World's Medical Knowledge into 970K

Dec 22, 2025

•

Huu-Hiep Nguyen

AI & ML interests

Recent Activity

Organizations

hiepnh's activity

Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries

Streaming datasets: 100x More Efficient

From Golden Gate Bridge to Broken JSON: Why Anthropic's SAE Steering Fails for Structured Output

Unlocking Healthcare AI: I'm Releasing State-of-the-Art Medical Models for Free. Forever.

OpenMed: Six Months of Open-Source Medical AI and the Road Ahead

The ML Engineer's Guide to Protein AI

NEO-unify: Building Native Multimodal Unified Models End to End

Visual Aesthetic Benchmark: Can Frontier Models Judge Beauty?

Create, Evaluate, and Connect AI Skills | SkillNet: A Large-Scale Agentic "Skill Graph" Knowledge Base

From GRPO to DAPO and GSPO: What, Why, and How

Mixture of Experts (MoEs) in Transformers

FINAL Bench: The Real Bottleneck to AGI Is Self-Correction

We Got Claude to Build CUDA Kernels and teach open models!

Slashing torch.compile Warmup & LoRA Swapping Times with Pruna

Tokenization in Transformers v5: Simpler, Clearer, and More Modular

The Great Classification Showdown: OSS vs BERT on Consumer Hardware

LightOnOCR-2-1B: a lightweight high-performance end-to-end OCR model family

Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment

Encoding the World's Medical Knowledge into 970K