Mateusz Dziemian's picture

Mateusz Dziemian

mattmdjaga

·

AI & ML interests

Interested in AI safety.

Recent Activity

authored a paper 21 days ago

Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition

authored a paper 21 days ago

Deceptive Automated Interpretability: Language Models Coordinating to Fool Oversight Systems

upvoted a paper 21 days ago

Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition

View all activity

Organizations

upvoted a paper 21 days ago

Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition

Paper • 2507.20526 • Published Jul 28 • 1

upvoted a paper 4 months ago

Antidistillation Sampling

Paper • 2504.13146 • Published Apr 17 • 61

upvoted 2 papers 10 months ago

Applying Refusal-Vector Ablation to Llama 3.1 70B Agents

Paper • 2410.10871 • Published Oct 8, 2024 • 1

AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents

Paper • 2410.09024 • Published Oct 11, 2024 • 1

upvoted 2 papers over 1 year ago

PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

Paper • 2403.04692 • Published Mar 7, 2024 • 42

Chain-of-Thought Reasoning Without Prompting

Paper • 2402.10200 • Published Feb 15, 2024 • 110

upvoted a collection over 1 year ago

Awesome SDXL LoRAs

A curated set of amazing Stable Diffusion XL LoRAs (they power the LoRA the Explorer Space) • 36 items • Updated Jun 24, 2024 • 27