🏝️ On Vacation

Yasunori Ozaki PRO

alfredplpl

·

https://alfredplpl.github.io/en/index.html

AI & ML interests

Computer Vision, LLM

Recent Activity

liked a model about 21 hours ago

CohereLabs/North-Micro-Vision-Instruct

liked a model about 22 hours ago

Qwen/Qwen3.8-2.4T-A95B

liked a model 1 day ago

Comfy-Org/gemma-4

View all activity

Organizations

upvoted a collection 1 day ago

LTX-2.5

LTX-2.5 base models, quantized models and accompanying LoRAs and IC-LoRAs • 4 items • Updated 2 days ago • 36

upvoted a collection 3 days ago

Muse Glimmer

Muse Glimmer 30B: multimodal agentic model for local deployment. BF16 weights, GGUF k-quants, ExecuTorch builds, DFlash drafter. • 4 items • Updated 3 days ago • 85

upvoted a collection 12 days ago

Kimi-K3-Abliterated

2 items • Updated 11 days ago • 4

upvoted a collection 13 days ago

Kimi K3 — De-Risked

2.8T LatentMoE + KDA, refusal-surface reduced at the weight level (ABLITERATED). GGUF variants need llama.cpp PR #26185 — mainline cannot load them. • 4 items • Updated 8 days ago • 2

upvoted a collection 16 days ago

Kimi K3

Open Frontier Intelligence • 2 items • Updated 15 days ago • 110

upvoted an article 23 days ago

Article

Security incident disclosure — July 2026

system

•

29 days ago

• 771

upvoted a changelog 27 days ago

Hugging Face Changelog

Build Spaces with AI Agents

28 days ago

• 146

upvoted a collection 28 days ago

Inkling

Inkling is a versatile, customizable model that reasons over text, images, audio, with variable and efficient thinking effort. • 4 items • Updated 17 days ago • 54

upvoted 3 collections about 1 month ago

AnimeGen

AnimeGen Demos and Models • 5 items • Updated Jul 12 • 2

FLUX.2

Our second generation of FLUX • 21 items • Updated Apr 6 • 270

LingBot-Video

3 items • Updated Jul 8 • 24

upvoted a paper 3 months ago

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

Paper • 2605.21272 • Published May 20 • 4

upvoted 4 collections 3 months ago

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

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

6 items • Updated Jun 4 • 93

Jagle

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

MobileCLIP2

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

upvoted 4 papers 3 months ago

L2P: Unlocking Latent Potential for Pixel Generation

Paper • 2605.12013 • Published May 12 • 36

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