Erfan Shayegani 😈

Erfan-Shayegani

·

https://erfanshayegani.github.io/

AI & ML interests

AI Safety - Responsible AI - Multi-Modal Alignment

Recent Activity

upvoted a collection 10 days ago

liked a model about 1 month ago

Qwen/Qwen2.5-Omni-7B

liked a model about 2 months ago

nvidia/Cosmos-Reason2-2B

View all activity

Organizations

Papers 6

arxiv:2510.01670

arxiv:2504.03735

arxiv:2411.04291

arxiv:2406.02575

spaces 2

Trackio

Track and visualize data streams in real-time

BrowserGym Environment Server

Control and monitor automated environment interactions

models 22

Erfan-Shayegani/smolgrpo2-paddingRight

Erfan-Shayegani/smolgrpo2-paddingLeft

Erfan-Shayegani/Qwen2-0-5B-GRPO-vllm-trl

Erfan-Shayegani/wordle-grpo-Qwen3-1.7B-test

Text Generation • 2B • Updated Feb 5 • 1

Erfan-Shayegani/browsergym-grpo-functiongemma-270m-it

Erfan-Shayegani/Qwen2.5-VL-3B-Instruct-Thinking-GRPO-corrected-formatreward

Erfan-Shayegani/Qwen2.5-VL-3B-Instruct-Thinking-2

Erfan-Shayegani/Qwen2.5-VL-3B-Instruct-Thinking-GRPO

Erfan-Shayegani/Qwen2.5-VL-3B-Instruct-Thinking

Erfan-Shayegani/Qwen-3B-GRPO-gsm8k

datasets 0

None public yet