Zobrazeno 1 - 10
of 105
pro vyhledávání: '"Ahmadi, Saba"'
Fine-grained understanding of objects, attributes, and relationships between objects is crucial for visual-language models (VLMs). Existing benchmarks primarily focus on evaluating VLMs' capability to distinguish between two very similar \textit{capt
Externí odkaz:
http://arxiv.org/abs/2407.16772
We study the problem of online binary classification in settings where strategic agents can modify their observable features to receive a positive classification. We model the set of feasible manipulations by a directed graph over the feature space,
Externí odkaz:
http://arxiv.org/abs/2407.11619
A major challenge in defending against adversarial attacks is the enormous space of possible attacks that even a simple adversary might perform. To address this, prior work has proposed a variety of defenses that effectively reduce the size of this s
Externí odkaz:
http://arxiv.org/abs/2406.03458
Autor:
Ahmadi, Saba
Le sous-titrage d’images est la tâche de l’intelligence artificielle (IA) qui consiste à décrire des images en langage naturel. Cette tâche d’IA a plusieurs applications sociétales utiles, telles que l’accessibilité pour les malvoyants,
Externí odkaz:
http://hdl.handle.net/1866/32688
Autor:
Ahmadi, Saba, Agrawal, Aishwarya
Recently, reference-free metrics such as CLIPScore (Hessel et al., 2021), UMIC (Lee et al., 2021), and PAC-S (Sarto et al., 2023) have been proposed for automatic reference-free evaluation of image captions. Our focus lies in evaluating the robustnes
Externí odkaz:
http://arxiv.org/abs/2305.14998
A fundamental problem in robust learning is asymmetry: a learner needs to correctly classify every one of exponentially-many perturbations that an adversary might make to a test-time natural example. In contrast, the attacker only needs to find one s
Externí odkaz:
http://arxiv.org/abs/2303.08944
We study the problem of online binary classification where strategic agents can manipulate their observable features in predefined ways, modeled by a manipulation graph, in order to receive a positive classification. We show this setting differs in f
Externí odkaz:
http://arxiv.org/abs/2302.12355
Autor:
Mañas, Oscar, Rodriguez, Pau, Ahmadi, Saba, Nematzadeh, Aida, Goyal, Yash, Agrawal, Aishwarya
Large pre-trained models have proved to be remarkable zero- and (prompt-based) few-shot learners in unimodal vision and language tasks. We propose MAPL, a simple and parameter-efficient method that reuses frozen pre-trained unimodal models and levera
Externí odkaz:
http://arxiv.org/abs/2210.07179
Autor:
Ahmadi, Saba, Awasthi, Pranjal, Khuller, Samir, Kleindessner, Matthäus, Morgenstern, Jamie, Sukprasert, Pattara, Vakilian, Ali
In this paper, we propose a natural notion of individual preference (IP) stability for clustering, which asks that every data point, on average, is closer to the points in its own cluster than to the points in any other cluster. Our notion can be mot
Externí odkaz:
http://arxiv.org/abs/2207.03600
We consider the problem of helping agents improve by setting short-term goals. Given a set of target skill levels, we assume each agent will try to improve from their initial skill level to the closest target level within reach or do nothing if no ta
Externí odkaz:
http://arxiv.org/abs/2203.00134