specimba

specimba's activity

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

upvoted an article 3 days ago

view article

Article

Security incident disclosure — July 2026

• 

system

•

4 days ago

• 174

upvoted 2 changelogs 4 days ago

view changelog

Hugging Face Changelog

Fine-Grained Token Presets

6 days ago

• 44

view changelog

Hugging Face Changelog

Build Spaces with AI Agents

4 days ago

• 94

upvoted a paper 11 days ago

Direct Preference Optimization: Your Language Model is Secretly a Reward Model

Paper • 2305.18290 • Published May 29, 2023 • 68

upvoted a collection 11 days ago

My models: daily driver rotation

Collection

A rotating list of models I created and currently use as daily drivers. From my many models, these are the ones I’m actively using. • 7 items • Updated 3 days ago • 10

upvoted 2 papers 14 days ago

Editing Models with Task Arithmetic

Paper • 2212.04089 • Published Dec 8, 2022 • 9

Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models

Paper • 2606.03748 • Published Jun 2 • 19

upvoted 4 changelogs 19 days ago

view changelog

Hugging Face Changelog

Publish models from CI without HF_TOKEN

Jun 8

• 131

view changelog

Hugging Face Changelog

Service Accounts for Enterprise organizations

Jun 12

• 154

view changelog

Hugging Face Changelog

Share your feedback with us

24 days ago

• 133

view changelog

Hugging Face Changelog

Filter Models page by Hardware

20 days ago

• 202

upvoted a collection 19 days ago

HunyuanVideo-1.5

Collection

8 items • Updated Dec 7, 2025 • 7

upvoted 4 papers 19 days ago

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

Paper • 2605.18719 • Published May 18 • 7

Qwen-Image-2.0 Technical Report

Paper • 2605.10730 • Published May 11 • 118

ERNIE-Image Technical Report

Paper • 2605.25347 • Published May 25 • 2

Qwen-Image-2.0-RL Technical Report

Paper • 2606.27608 • Published 25 days ago • 50

upvoted an article 20 days ago

view article

Article

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

• 

FINAL-Bench

•

21 days ago

• 19

upvoted 2 papers 21 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 21 days ago

Gemma 4 — DECKARD HERETIC, Multimodal & Speculators

Collection

Gemma 4 abliterated/quantized — DECKARD HERETIC 31B, SuperGemma4-26B multimodal, 26B-A4B MoE, plus EAGLE3/DFlash drafters. • 14 items • Updated 18 days ago • 8