Zobrazeno 1 - 10
of 15 369
pro vyhledávání: '"P Milad"'
Autor:
Qi, Xiangyu, Wei, Boyi, Carlini, Nicholas, Huang, Yangsibo, Xie, Tinghao, He, Luxi, Jagielski, Matthew, Nasr, Milad, Mittal, Prateek, Henderson, Peter
Stakeholders -- from model developers to policymakers -- seek to minimize the dual-use risks of large language models (LLMs). An open challenge to this goal is whether technical safeguards can impede the misuse of LLMs, even when models are customiza
Externí odkaz:
http://arxiv.org/abs/2412.07097
Autor:
Fotouhi, Milad, Bahadori, Mohammad Taha, Feyisetan, Oluwaseyi, Arabshahi, Payman, Heckerman, David
The existing algorithms for identification of neurons responsible for undesired and harmful behaviors do not consider the effects of confounders such as topic of the conversation. In this work, we show that confounders can create spurious correlation
Externí odkaz:
http://arxiv.org/abs/2412.02893
Autor:
Zhao, Xuandong, Gunn, Sam, Christ, Miranda, Fairoze, Jaiden, Fabrega, Andres, Carlini, Nicholas, Garg, Sanjam, Hong, Sanghyun, Nasr, Milad, Tramer, Florian, Jha, Somesh, Li, Lei, Wang, Yu-Xiang, Song, Dawn
As the outputs of generative AI (GenAI) techniques improve in quality, it becomes increasingly challenging to distinguish them from human-created content. Watermarking schemes are a promising approach to address the problem of distinguishing between
Externí odkaz:
http://arxiv.org/abs/2411.18479
Autor:
Masroor, Milad, Hassan, Tahir, Tian, Yu, Wells, Kevin, Rosewarne, David, Do, Thanh-Toan, Carneiro, Gustavo
Deep learning has achieved remarkable success in image classification and segmentation tasks. However, fairness concerns persist, as models often exhibit biases that disproportionately affect demographic groups defined by sensitive attributes such as
Externí odkaz:
http://arxiv.org/abs/2411.11939
We present a framework for learning a single policy capable of producing all quadruped gaits and transitions. The framework consists of a policy trained with deep reinforcement learning (DRL) to modulate the parameters of a system of abstract oscilla
Externí odkaz:
http://arxiv.org/abs/2411.04787
Safety Verification for Evasive Collision Avoidance in Autonomous Vehicles with Enhanced Resolutions
Autor:
Arab, Aliasghar, Khaleghi, Milad, Partovi, Alireza, Abbaspour, Alireza, Shinde, Chaitanya, Mousavi, Yashar, Azimi, Vahid, Karimmoddini, Ali
This paper presents a comprehensive hazard analysis, risk assessment, and loss evaluation for an Evasive Minimum Risk Maneuvering (EMRM) system designed for autonomous vehicles. The EMRM system is engineered to enhance collision avoidance and mitigat
Externí odkaz:
http://arxiv.org/abs/2411.02706
Autor:
Bahri, Ali, Yazdanpanah, Moslem, Noori, Mehrdad, Oghani, Sahar Dastani, Cheraghalikhani, Milad, Osowiech, David, Beizaee, Farzad, vargas-hakim, Gustavo adolfo., Ayed, Ismail Ben, Desrosiers, Christian
Test-Time Adaptation (TTA) addresses distribution shifts during testing by adapting a pretrained model without access to source data. In this work, we propose a novel TTA approach for 3D point cloud classification, combining sampling variation with w
Externí odkaz:
http://arxiv.org/abs/2411.01116
A quantum analogue of the Central Limit Theorem (CLT), first introduced by Cushen and Hudson (1971), states that the $n$-fold convolution $\rho^{\boxplus n}$ of an $m$-mode quantum state $\rho$ with zero first moments and finite second moments conver
Externí odkaz:
http://arxiv.org/abs/2410.21998
Fully quantum conditional entropies play a central role in quantum information theory and cryptography, where they measure the uncertainty about a quantum system from the perspective of an observer with access to a potentially correlated system. Thro
Externí odkaz:
http://arxiv.org/abs/2410.21976
Autor:
Nori, Milad Khademi, Kim, Il-Min
In class-incremental learning (class-IL), models must classify all previously seen classes at test time without task-IDs, leading to task confusion. Despite being a key challenge, task confusion lacks a theoretical understanding. We present a novel m
Externí odkaz:
http://arxiv.org/abs/2410.20768