AI Safety Research's picture

AI Safety Research

AISafety

·

https://humanaligned.ai

AI & ML interests

LLMs, planning, EA

Recent Activity

new activity about 13 hours ago

LiquidAI/LFM2-ColBERT:Scores

liked a Space about 13 hours ago

LiquidAI/LFM2-ColBERT

liked a model 12 days ago

ByteDance/Ouro-2.6B-Thinking

View all activity

Organizations

upvoted an article 21 days ago

Article

EuroLLM-9B

By

and 5 others •

Dec 2, 2024

• 137

upvoted a collection 27 days ago

⚛️ Liquid Nanos

Library of task-specific models: https://www.liquid.ai/blog/introducing-liquid-nanos-frontier-grade-performance-on-everyday-devices • 21 items • Updated 13 days ago • 92

upvoted an article 27 days ago

Article

SOTA OCR with Core ML and dots.ocr

Oct 2

• 58

upvoted a collection about 1 month ago

DeepSeek-V3.2

2 items • Updated Sep 29 • 447

upvoted a paper about 2 months ago

Reinforcement Learning on Pre-Training Data

Paper • 2509.19249 • Published Sep 23 • 67

upvoted 2 collections 3 months ago

InternVL3.5

This collection includes all released checkpoints of InternVL3.5, covering different training stages (e.g., Pretraining, SFT, MPO, Cascade RL). • 54 items • Updated Sep 28 • 102

DeepSeek-V3.1

4 items • Updated Sep 22 • 245

upvoted an article 3 months ago

Article

Introducing AI Sheets: a tool to work with datasets using open AI models!

Aug 8

• 102

upvoted a paper 3 months ago

GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

Paper • 2508.06471 • Published Aug 8 • 189

upvoted 3 collections 4 months ago

GLM-4.5

GLM-4.5: An open-source large language model designed for intelligent agents by Z.ai • 11 items • Updated Aug 11 • 248

Sparse Autoencoders

SAEs are tools for understanding the internal representations of neural networks. These can be loaded using https://github.com/EleutherAI/sae • 9 items • Updated Feb 26 • 5

Hunyuan-A13B

5 items • Updated 8 days ago • 24

upvoted a paper 4 months ago

Seed1.5-VL Technical Report

Paper • 2505.07062 • Published May 11 • 152

upvoted an article 6 months ago

Article

Good answers are not necessarily factual answers: an analysis of hallucination in leading LLMs

By

and 1 other •

May 7

• 41

upvoted a collection 7 months ago

Qwen3

Qwen's new Qwen3 models. In Unsloth Dynamic 2.0, GGUF, 4-bit and 16-bit Safetensor formats. Includes 128K Context Length variants. • 79 items • Updated 12 days ago • 230

upvoted an article 7 months ago

Article

Mixture of Tunable Experts - Behavior Modification of DeepSeek-R1 at Inference Time

By

and 4 others •

Feb 18

• 35

upvoted a collection 7 months ago

Granite Experiments

Experimental projects under consideration for the Granite family. • 20 items • Updated 11 days ago • 15

upvoted a paper 7 months ago

OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens

Paper • 2504.07096 • Published Apr 9 • 76

upvoted a collection 7 months ago

Cogito v1 Preview

5 items • Updated Apr 8 • 120

upvoted an article 8 months ago

Article

Open R1: Update #3

By

and 9 others •

Mar 11

• 295