2 citations · 4 across the 5 of their papers we have counts for
7 papers
Configurable Reward Model for Balanced Safety Alignment
Zhengping Jiang, Mehran Khodabandeh, Akash Bharadwaj +5
Aligning large language models (LLMs) to heterogeneous and rapidly evolving safety requirements remains a critical challenge. Existing instruction-tuned LLMs and standalone safety…
Jailbreak-Zero: A Path to Pareto Optimal Red Teaming for Large Language Models
Kai Hu, Abhinav Aggarwal, Mehran Khodabandeh +6
This paper introduces Jailbreak-Zero, a novel red teaming methodology that shifts the paradigm of Large Language Model (LLM) safety evaluation from a constrained example-based appr…
A Robust Learning Approach to Domain Adaptive Object Detection
Mehran Khodabandeh, Arash Vahdat, Mani Ranjbar +1
Domain shift is unavoidable in real-world applications of object detection. For example, in self-driving cars, the target domain consists of unconstrained road environments which c…
Distribution Aware Active Learning
Arash Mehrjou, Mehran Khodabandeh, Greg Mori
Discriminative learning machines often need a large set of labeled samples for training. Active learning (AL) settings assume that the learner has the freedom to ask an oracle to l…
DIY Human Action Data Set Generation
Mehran Khodabandeh, Hamid Reza Vaezi Joze, Ilya Zharkov +1
The recent successes in applying deep learning techniques to solve standard computer vision problems has aspired researchers to propose new computer vision problems in different do…
Active Learning for Structured Prediction from Partially Labeled Data
Mehran Khodabandeh, Zhiwei Deng, Mostafa S. Ibrahim +2
We propose a general purpose active learning algorithm for structured prediction, gathering labeled data for training a model that outputs a set of related labels for an image or v…
Discovering Human Interactions in Videos with Limited Data Labeling
Mehran Khodabandeh, Arash Vahdat, Guang-Tong Zhou +4
We present a novel approach for discovering human interactions in videos. Activity understanding techniques usually require a large number of labeled examples, which are not availa…