Hamid Kazemi's picture

Hamid Kazemi

seyedhamidreza

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 10 days ago

A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language Models

upvoted a paper 10 days ago

What do we learn from inverting CLIP models?

authored a paper 15 days ago

A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language Models

View all activity

Organizations

upvoted 2 papers 10 days ago

A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language Models

Paper • 2605.08513 • Published 20 days ago • 15

What do we learn from inverting CLIP models?

Paper • 2403.02580 • Published Mar 5, 2024 • 4

upvoted a paper 7 months ago

Reasoning's Razor: Reasoning Improves Accuracy but Can Hurt Recall at Critical Operating Points in Safety and Hallucination Detection

Paper • 2510.21049 • Published Oct 23, 2025 • 3

upvoted a paper about 1 year ago

RePanda: Pandas-powered Tabular Verification and Reasoning

Paper • 2503.11921 • Published Mar 14, 2025 • 2

upvoted a paper over 1 year ago

SALSA: Soup-based Alignment Learning for Stronger Adaptation in RLHF

Paper • 2411.01798 • Published Nov 4, 2024 • 8

upvoted a paper about 2 years ago

Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text

Paper • 2401.12070 • Published Jan 22, 2024 • 45