Yasunori Ozaki PRO

alfredplpl's activity

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

upvoted a collection about 17 hours ago

Kimi K3 — De-Risked

Collection

2.8T LatentMoE + KDA, refusal-surface reduced at the weight level (ABLITERATED). GGUF variants need llama.cpp PR #26185 — mainline cannot load them. • 5 items • Updated about 16 hours ago • 1

upvoted a collection 4 days ago

Kimi K3

Collection

Open Frontier Intelligence • 2 items • Updated 3 days ago • 88

upvoted an article 11 days ago

view article

Article

Security incident disclosure — July 2026

• 

system

•

16 days ago

• 729

upvoted a changelog 15 days ago

view changelog

Hugging Face Changelog

Build Spaces with AI Agents

16 days ago

• 133

upvoted a collection 16 days ago

Inkling

Collection

Inkling is a versatile, customizable model that reasons over text, images, audio, with variable and efficient thinking effort. • 4 items • Updated 4 days ago • 41

upvoted a collection 19 days ago

AnimeGen

Collection

AnimeGen Demos and Models • 5 items • Updated 19 days ago • 2

upvoted a collection 22 days ago

FLUX.2

Collection

Our second generation of FLUX • 21 items • Updated Apr 6 • 263

upvoted a collection 23 days ago

LingBot-Video

Collection

3 items • Updated 24 days ago • 22

upvoted a paper 2 months ago

MONET: A Massive, Open, Non-redundant and Enriched Text-to-image dataset

Paper • 2605.21272 • Published May 20 • 4

upvoted 4 collections 2 months ago

MONET - Massive Open Non-redundant, Enriched, Text-to-image

Collection

A curated, deduped & recaptioned open image–text dataset of 104.9M samples released under the Apache2.0 licence. https://huggingface.co/blog/jasperai/ • 4 items • Updated May 28 • 11

Bonsai Image

Collection

6 items • Updated Jun 4 • 93

Jagle

Collection

Jagle: Building a Large-Scale Japanese Multimodal Post-Training Dataset for Vision–Language Models • 5 items • Updated Apr 12 • 2

MobileCLIP2

Collection

MobileCLIP2: Mobile-friendly image-text models with SOTA zero-shot capabilities trained on DFNDR-2B • 30 items • Updated Apr 23 • 64

upvoted a paper 2 months ago

L2P: Unlocking Latent Potential for Pixel Generation

Paper • 2605.12013 • Published May 12 • 36

upvoted 6 papers 3 months ago

Asymmetric Flow Models

Paper • 2605.12964 • Published May 13 • 23

Qwen-Image-VAE-2.0 Technical Report

Paper • 2605.13565 • Published May 13 • 62

Qwen-Image-2.0 Technical Report

Paper • 2605.10730 • Published May 11 • 118

STARFlow2: Bridging Language Models and Normalizing Flows for Unified Multimodal Generation

Paper • 2605.08029 • Published May 8 • 12

Continuous-Time Distribution Matching for Few-Step Diffusion Distillation

Paper • 2605.06376 • Published May 7 • 27

Continuous Latent Diffusion Language Model

Paper • 2605.06548 • Published May 7 • 87