🔄 In a Training Loop

specimba

specimba

·

AI & ML interests

everything

Recent Activity

liked a dataset about 4 hours ago

markov-ai/gaming-500-hours

liked a dataset about 11 hours ago

Qwen/Qwen-Image-Bench

upvoted a changelog about 12 hours ago

Publish models from CI without HF_TOKEN

View all activity

Organizations

upvoted 4 changelogs about 12 hours ago

Hugging Face Changelog

Publish models from CI without HF_TOKEN

23 days ago

• 117

Hugging Face Changelog

Service Accounts for Enterprise organizations

19 days ago

• 139

Hugging Face Changelog

Share your feedback with us

6 days ago

• 92

Hugging Face Changelog

Filter Models page by Hardware

1 day ago

• 59

upvoted a collection about 13 hours ago

HunyuanVideo-1.5

8 items • Updated Dec 7, 2025 • 7

upvoted 2 papers about 13 hours ago

SafeDiffusion-R1: Online Reward Steering for Safe Diffusion Post-Training

Paper • 2605.18719 • Published May 18 • 6

Qwen-Image-2.0 Technical Report

Paper • 2605.10730 • Published May 11 • 116

upvoted 2 papers about 14 hours ago

ERNIE-Image Technical Report

Paper • 2605.25347 • Published May 25 • 1

Qwen-Image-2.0-RL Technical Report

Paper • 2606.27608 • Published 7 days ago • 46

upvoted an article 1 day ago

Article

Chitos: From Detection to Proof — An Autonomous Security AI That Actually Exploits

FINAL-Bench

•

3 days ago

• 19

upvoted 2 papers 3 days ago

Refusal in Language Models Is Mediated by a Single Direction

Paper • 2406.11717 • Published Jun 17, 2024 • 15

Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable

Paper • 2503.00555 • Published Mar 1, 2025 • 3

upvoted a collection 3 days ago

Gemma 4 — DECKARD HERETIC, Multimodal & Speculators

Gemma 4 abliterated/quantized — DECKARD HERETIC 31B, SuperGemma4-26B multimodal, 26B-A4B MoE, plus EAGLE3/DFlash drafters. • 9 items • Updated 22 days ago • 7

upvoted 2 papers 6 days ago

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

Paper • 2511.22699 • Published Nov 27, 2025 • 248

SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

Paper • 2502.14786 • Published Feb 20, 2025 • 167

upvoted 2 collections 6 days ago

Krea 2 LoRAs

A collection of LoRAs for Krea 2 Turbo and Krea 2 Raw • 9 items • Updated 8 days ago • 34

FLUX.2

Our second generation of FLUX • 21 items • Updated Apr 6 • 250

upvoted 2 collections 7 days ago

Qwen3.5-Claude-Fable-5

Our series of Qwen3.5 finetunes on Claude-Fable-5 outputs • 2 items • Updated 12 days ago • 5

Qwen3.5-Claude-Mythos-5

A collection of our uncensored Claude Mythos fine tunes • 2 items • Updated 12 days ago • 23

upvoted a paper 9 days ago

Agentic Entropy-Balanced Policy Optimization

Paper • 2510.14545 • Published Oct 16, 2025 • 109