Yamata Zen

yamatazen's activity

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

upvoted a paper 4 days ago

Towards Interactive Intelligence for Digital Humans

Paper • 2512.13674 • Published 5 days ago • 9

upvoted a paper 5 days ago

Fairy2i: Training Complex LLMs from Real LLMs with All Parameters in {pm 1, pm i}

Paper • 2512.02901 • Published 18 days ago • 5

upvoted a paper 7 days ago

SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training

Paper • 2506.05301 • Published Jun 5 • 58

upvoted a changelog 8 days ago

view changelog

Changelog

HuggingChat for Docs

8 days ago

• 72

upvoted 2 papers 10 days ago

Terrain Diffusion: A Diffusion-Based Successor to Perlin Noise in Infinite, Real-Time Terrain Generation

Paper • 2512.08309 • Published 11 days ago • 2

SignRoundV2: Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs

Paper • 2512.04746 • Published 16 days ago • 13

upvoted a paper 12 days ago

LongCat-Image Technical Report

Paper • 2512.07584 • Published 12 days ago • 18

upvoted a changelog 12 days ago

view changelog

Changelog

Team & Enterprise Articles Now Featured on the Hugging Face Blog

12 days ago

• 63

upvoted 2 papers 12 days ago

PaCo-RL: Advancing Reinforcement Learning for Consistent Image Generation with Pairwise Reward Modeling

Paper • 2512.04784 • Published 18 days ago • 24

EditThinker: Unlocking Iterative Reasoning for Any Image Editor

Paper • 2512.05965 • Published 15 days ago • 36

upvoted a paper 13 days ago

DraCo: Draft as CoT for Text-to-Image Preview and Rare Concept Generation

Paper • 2512.05112 • Published 16 days ago • 11

upvoted an article 15 days ago

view article

Article

DeLERP: Decomposed Linear Interpolation for Model Merging

• 

about 1 month ago

•

7

upvoted a paper 15 days ago

Aligned but Stereotypical? The Hidden Influence of System Prompts on Social Bias in LVLM-Based Text-to-Image Models

Paper • 2512.04981 • Published 16 days ago • 7

upvoted an article 15 days ago

view article

Article

Norm-Preserving Biprojected Abliteration

• 

Nov 6

•

56

upvoted a collection 15 days ago

Ovis-Image

Collection

Ovis-Image is a 7B text-to-image model specifically optimized for high-quality text rendering under stringent computational constraints. • 7 items • Updated 17 days ago • 6

upvoted a paper 16 days ago

AdaMuon: Adaptive Muon Optimizer

Paper • 2507.11005 • Published Jul 15 • 2

upvoted 3 papers 17 days ago

Qwen3-VL Technical Report

Paper • 2511.21631 • Published 24 days ago • 129

Decoupled DMD: CFG Augmentation as the Spear, Distribution Matching as the Shield

Paper • 2511.22677 • Published 23 days ago • 27

DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

Paper • 2512.02556 • Published 18 days ago • 219

upvoted a paper 20 days ago

Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer

Paper • 2511.22699 • Published 23 days ago • 204