Erfan Shayegani 😈's picture

Erfan Shayegani 😈

Erfan-Shayegani

·

https://erfanshayegani.github.io/

AI & ML interests

AI Safety - Responsible AI - Multi-Modal Alignment

Recent Activity

authored a paper 9 days ago

Misaligned Roles, Misplaced Images: Structural Input Perturbations Expose Multimodal Alignment Blind Spots

authored a paper 9 days ago

Unfair Alignment: Examining Safety Alignment Across Vision Encoder Layers in Vision-Language Models

upvoted a paper about 1 month ago

R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model

View all activity

Organizations

Erfan-Shayegani's activity

upvoted a paper about 1 month ago

R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model

Paper • 2503.05132 • Published Mar 7 • 57

upvoted a paper 5 months ago

LLaVA-o1: Let Vision Language Models Reason Step-by-Step

Paper • 2411.10440 • Published Nov 15, 2024 • 124

upvoted an article 7 months ago

Article

Mixture of Experts Explained

Dec 11, 2023

• 570

upvoted an article 8 months ago

Article

Welcome Llama 3 - Meta's new open LLM

Apr 18, 2024

• 287

upvoted a collection 8 months ago

Phi-3

Phi-3 family of small language and multi-modal models. Language models are available in short- and long-context lengths. • 26 items • Updated 5 days ago • 566

upvoted an article 8 months ago

Article

Llama 3.1 - 405B, 70B & 8B with multilinguality and long context

Jul 23, 2024

• 232

upvoted an article 9 months ago

Article

Google releases Gemma 2 2B, ShieldGemma and Gemma Scope

Jul 31, 2024

• 58