Haoyuan WU

hywu's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 2 months ago

LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model

Paper • 2604.20796 • Published Apr 22 • 244

upvoted a paper 3 months ago

HY-WU (Part I): An Extensible Functional Neural Memory Framework and An Instantiation in Text-Guided Image Editing

Paper • 2603.07236 • Published Mar 7 • 3

upvoted 2 papers 6 months ago

Nested Learning: The Illusion of Deep Learning Architectures

Paper • 2512.24695 • Published Dec 31, 2025 • 46

Diversity or Precision? A Deep Dive into Next Token Prediction

Paper • 2512.22955 • Published Dec 28, 2025 • 10

upvoted a paper 8 months ago

Knocking-Heads Attention

Paper • 2510.23052 • Published Oct 27, 2025 • 30

upvoted 2 papers 9 months ago

One-Token Rollout: Guiding Supervised Fine-Tuning of LLMs with Policy Gradient

Paper • 2509.26313 • Published Sep 30, 2025 • 5

Reinforcement Learning on Pre-Training Data

Paper • 2509.19249 • Published Sep 23, 2025 • 67

upvoted a collection 10 months ago

GroveMoE

Collection

3 items • Updated Aug 22, 2025 • 1

upvoted a paper 10 months ago

Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks

Paper • 2401.02731 • Published Jan 5, 2024 • 3

upvoted a collection 10 months ago

GroveMoE

Collection

GroveMoE is an open-source family of large language models developed by the AGI Center, Ant Research Institute. • 3 items • Updated 12 days ago • 9

upvoted a paper 11 months ago

Grove MoE: Towards Efficient and Superior MoE LLMs with Adjugate Experts

Paper • 2508.07785 • Published Aug 11, 2025 • 30

upvoted an article over 1 year ago

view article

Article

Putting RL back in RLHF

• 
• 

vwxyzjn, ArashAhmadian

•

Jun 12, 2024

• 111

upvoted 3 collections over 1 year ago

Camelidae

Collection

5 items • Updated Aug 22, 2025 • 2

Cosmos-Preidct1

Collection

⚠️ This collection is archived. 👉 https://huggingface.co/collections/nvidia/cosmos3 • 14 items • Updated 15 days ago • 304

Tulu 3 Datasets

Collection

All datasets released with Tulu 3 -- state of the art open post-training recipes. • 32 items • Updated Mar 2 • 100