AI Safety Research

AISafety

·

https://humanaligned.ai

AI & ML interests

LLMs, planning, EA

Recent Activity

upvoted a collection about 8 hours ago

liked a Space 5 days ago

smolagents/hf-realtime-voice

upvoted an article 7 days ago

Borealis — open data, code, weights recipe for training Audio LLM

View all activity

Organizations

upvoted a collection about 8 hours ago

💧 LFM2.5

Collection of post-trained and base LFM2.5 models. • 16 items • Updated 13 days ago • 203

upvoted an article 7 days ago

Article

Borealis — open data, code, weights recipe for training Audio LLM

AlexWortega

•

May 25

• 16

upvoted a collection 10 days ago

Instella-MoE ✨

Family of fully open 16B MoE LLM with 2.8B active params per token, trained on AMD Instinct™ MI300 & MI325 GPUs. • 6 items • Updated 20 days ago • 18

upvoted an article 26 days ago

Article

Security incident disclosure — July 2026

system

•

Jul 16

• 775

upvoted a paper 26 days ago

Weak-to-Strong Generalization via Direct On-Policy Distillation

Paper • 2607.05394 • Published Jul 8 • 147

upvoted a paper 27 days ago

Loop the Loopies!

Paper • 2607.16051 • Published Jul 17 • 77

upvoted 2 collections about 1 month ago

NLA Models

Natural Language Autoencoders across Llama, Gemma, and Qwen. Code: https://github.com/kitft/natural_language_autoencoders/ • 8 items • Updated May 6 • 17

NVFP4

Dynamic Unsloth NVFP4 Quants. Faster and more accurate. • 11 items • Updated 3 days ago • 61

upvoted a paper about 2 months ago

S-Agent: Spatial Tool-Use Elicits Reasoning for Spatial Intelligence

Paper • 2606.20515 • Published Jun 18 • 41

upvoted 3 collections 2 months ago

PP-OCRv6

From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks • 20 items • Updated 3 days ago • 109

DeepSeek-V4

8 items • Updated 4 days ago • 830

Ideogram 4

8 items • Updated Jun 4 • 68

upvoted a collection 3 months ago

Bonsai Image

6 items • Updated Jun 4 • 93

upvoted a paper 3 months ago

SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer

Paper • 2605.15178 • Published May 14 • 91

upvoted a collection 3 months ago

Step-3.5-Flash

step 3.5 models • 9 items • Updated Mar 14 • 40

upvoted a collection 4 months ago

Qwen-Scope

16 items • Updated May 14 • 77

upvoted 2 collections 5 months ago

ShareGPT Datasets

22 items • Updated Mar 2 • 17

Mistral Small 4

A state-of-the-art model, open-weight, with a granular Mixture-of-Experts architecture that fuses instruct, reasoning and agentic skills. • 3 items • Updated Mar 16 • 77

upvoted 2 articles 8 months ago

Article

Exploring Environments Hub: Your Language Model needs better (open) environments to learn

anakin87

•

Sep 4, 2025

• 32

Article

HUMAINE: A Rigorous Framework for Understanding AI Through Human Experience

ProlificAI

•

Sep 16, 2025

• 7