2 13 21

Erfan Shayegani 😈

Erfan-Shayegani

https://erfanshayegani.github.io/

AI & ML interests

AI Safety - Responsible AI - Multi-Modal Alignment

Recent Activity

authored a paper 2 days ago

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

authored a paper 2 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

liked a model about 1 month ago

CohereLabs/aya-vision-8b

Image-Text-to-Text • Updated about 6 hours ago • 21.4k • • 279

liked 3 models 3 months ago

liked a dataset 6 months ago

CohereLabs/aya_redteaming

Viewer • Updated about 19 hours ago • 7.42k • 29 • 23

liked a model 6 months ago

CohereLabs/aya-expanse-8b

Text Generation • Updated about 6 hours ago • 35.3k • • 359

liked a Space 6 months ago

309

Aya Models

🌍

Interact with the Aya family of models.

liked a model 6 months ago

CohereLabs/aya-expanse-32b

Text Generation • Updated about 6 hours ago • 10.4k • • 246

liked a Space 7 months ago

358

Reward Bench Leaderboard

📐

Explore and analyze RewardBench leaderboard data

liked 2 models 7 months ago

black-forest-labs/FLUX.1-schnell

Text-to-Image • Updated Aug 16, 2024 • 1.43M • • 3.65k

black-forest-labs/FLUX.1-dev

Text-to-Image • Updated Aug 16, 2024 • 2.06M • • 9.83k

liked 3 models 8 months ago

Efficient-Large-Model/VILA1.5-3b

Text Generation • Updated Jul 18, 2024 • 12.2k • 26

microsoft/Phi-3.5-mini-instruct

Text Generation • Updated Mar 2 • 297k • • 851

THUDM/CogVideoX-2b

Text-to-Video • Updated Nov 23, 2024 • 31.3k • 324

liked 3 models 9 months ago

LinWeizheDragon/PreFLMR_ViT-G

Feature Extraction • Updated Feb 27, 2024 • 487 • 8

google/shieldgemma-2b

Text Generation • Updated Aug 28, 2024 • 3.5k • 69

meta-llama/Prompt-Guard-86M

Text Classification • Updated Jul 25, 2024 • 28.4k • 247

liked 2 datasets 9 months ago

sorry-bench/sorry-bench-202406

Viewer • Updated Jul 2, 2024 • 9.45k • 396 • 20

mehrankazemi/ReMI

Viewer • Updated Oct 22, 2024 • 2.63k • 370 • 12

liked a model 11 months ago

liuhaotian/llava-v1.5-7b

Image-Text-to-Text • Updated May 8, 2024 • 1.27M • 447