👋 Open to Work

Atif Quamar

atifquamar07

2

P(doom) 10%

·

https://www.atifquamar.com

AI & ML interests

reasoning in language models, reinforcement learning, ai safety

Recent Activity

upvoted a paper 2 days ago

Noise Out, Bias In: Targeted Bias Injection in Diffusion Language Models via Closed-Loop Activation Steering

upvoted a paper 2 days ago

Certification of Real Images through Calibrated Content Authentication

updated a model 4 months ago

atifquamar07/ministral-3-3b-math-hard-pc-grpo

View all activity

Organizations

models 11

atifquamar07/ministral-3-3b-math-hard-pc-grpo

Text Generation • 4B • Updated May 26 • 11

atifquamar07/llama-3.1-8b-imdb

Updated Jul 29, 2025

atifquamar07/Qwen2.5-7B-imdb

Updated Jul 29, 2025

atifquamar07/Mistral-7B-v0.1-imdb

Updated Jul 29, 2025

atifquamar07/pythia-6.9b-imdb

Updated Jul 29, 2025

atifquamar07/llama-3.1-8b-rotten-tomatoes

Updated Jul 28, 2025

atifquamar07/mistral-zephyr-7b-HH-DPO

Updated Jul 28, 2025

atifquamar07/llama-3.1-Tulu-3-8b-HH-DPO

Updated Jul 27, 2025

atifquamar07/llama-3.1-8b-HH-DPO-0.5

Updated Jul 27, 2025

atifquamar07/llama-3.1-8b-HH-DPO

Updated Jul 25, 2025

datasets 0

None public yet