Arman Zharmagambetov — accepted AI-conference papers

2026

CIMemories: A Compositional Benchmark For Contextual Integrity In LLMs

Niloofar Mireshghallah, Neal Mangaokar, Narine Kokhlikyan, Arman Zharmagambetov, Manzil Zaheer, Saeed Mahloujifar +1

ICLR 2026poster

Large Language Models (LLMs) increasingly use persistent memory from past interactions to enhance personalization and task performance. However, this memory creates critical risks when sensitive information is revealed in inappropriate contexts. We present CIMemories, a benchmark for evaluating whet…

Cited by 0 Source ↗code ↗Scholar ↗

2026

Safety Alignment of LMs via Non-cooperative Games

Anselm Paulus, Ilia Kulikov, Brandon Amos, REMI MUNOS, Ivan Evtimov, Kamalika Chaudhuri +1

ICML 2026spotlight

Ensuring the safety of language models (LMs) while maintaining their usefulness remains a critical challenge in AI alignment. Current approaches rely on sequential adversarial training: generating adversarial prompts and fine-tuning LMs to defend against them. We introduce a different paradigm: fram…

Cited by 0 Source ↗Scholar ↗

2025

AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs

Anselm Paulus, Arman Zharmagambetov, Chuan Guo, Brandon Amos, Yuandong Tian

ICML 2025poster

Large Language Models (LLMs) are vulnerable to **jailbreaking attacks** that lead to generation of inappropriate or harmful content. Manual red-teaming requires a time-consuming search for adversarial prompts, whereas automatic adversarial prompt generation often leads to semantically meaningless a…

Cited by 88 Source ↗PDF ↗code ↗Scholar ↗

2025

AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents

Arman Zharmagambetov, Chuan Guo, Ivan Evtimov, Maya Pavlova, Ruslan Salakhutdinov, Kamalika Chaudhuri

NeurIPS 2025poster

Autonomous AI agents that can follow instructions and perform complex multi-step tasks have tremendous potential to boost human productivity. However, to perform many of these tasks, the agents need access to personal information from their users, raising the question of whether they are capable of…

Cited by 0 Source ↗code ↗Scholar ↗

2025

AlgoTune: Can Language Models Speed Up General-Purpose Numerical Programs?

Ori Press, Brandon Amos, Haoyu Zhao, Yikai Wu, Samuel Ainsworth, Dominik Krupke +18

NeurIPS 2025poster

Despite progress in language model (LM) capabilities, evaluations have thus far focused on models' performance on tasks that humans have previously solved, including in programming (SWE-Bench) and mathematics (FrontierMath). We therefore propose testing models' ability to design and implement algor…

Cited by 0 Source ↗Scholar ↗

2025

WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks

Ivan Evtimov, Arman Zharmagambetov, Aaron Grattafiori, Chuan Guo, Kamalika Chaudhuri

NeurIPS 2025poster

Autonomous UI agents powered by AI have tremendous potential to boost human productivity by automating routine tasks such as filing taxes and paying bills. However, a major challenge in unlocking their full potential is security, which is exacerbated by the agent's ability to take action on their us…

Cited by 0 Source ↗code ↗Scholar ↗

2024

Beyond the ROC Curve: Classification Trees Using Cost-Optimal Curves, with Application to Imbalanced Datasets

Magzhan Gabidolla, Arman Zharmagambetov, Miguel Á. Carreira-Perpiñán

ICML 2024poster

Important applications such as fraud or spam detection or churn prediction involve binary classification problems where the datasets are imbalanced and the cost of false positives greatly differs from the cost of false negatives. We focus on classification trees, in particular oblique trees, which s…

Cited by 4 Source ↗PDF ↗Scholar ↗

2024

Contrastive Predict-and-Search for Mixed Integer Linear Programs

Taoan Huang, Aaron M Ferber, Arman Zharmagambetov, Yuandong Tian, Bistra Dilkina

ICML 2024poster

Mixed integer linear programs (MILP) are flexible and powerful tools for modeling and solving many difficult real-world combinatorial optimization problems. In this paper, we propose a novel machine learning (ML)-based framework ConPaS that learns to predict solutions to MILPs with contrastive learn…

Cited by 5 Source ↗PDF ↗Scholar ↗

2024

GenCO: Generating Diverse Designs with Combinatorial Constraints

Aaron M Ferber, Arman Zharmagambetov, Taoan Huang, Bistra Dilkina, Yuandong Tian

ICML 2024poster

Deep generative models like GAN and VAE have shown impressive results in generating unconstrained objects like images. However, many design settings arising in industrial design, material science, computer graphics and more require that the generated objects satisfy hard combinatorial constraints or…

Cited by 1 Source ↗PDF ↗Scholar ↗

2024

To the Globe (TTG): Towards Language-Driven Guaranteed Travel Planning

Da Ju, Song Jiang, Andrew Cohen, Aaron Foss, Sasha Mitts, Arman Zharmagambetov +5

EMNLP 2024system demonstrations

Travel planning is a challenging and time-consuming task that aims to find an itinerary which satisfies multiple, interdependent constraints regarding flights, accommodations, attractions, and other travel arrangements. In this paper, we propose To the Globe (TTG), a real-time demo system that takes…

Cited by 4 Source ↗PDF ↗code ↗Scholar ↗

2023

Landscape Surrogate: Learning Decision Losses for Mathematical Optimization Under Partial Information

Arman Zharmagambetov, Brandon Amos, Aaron M Ferber, Taoan Huang, Bistra Dilkina, Yuandong Tian

NeurIPS 2023poster

Recent works in learning-integrated optimization have shown promise in settings where the optimization problem is only partially observed or where general-purpose optimizers perform poorly without expert tuning. By learning an optimizer $\mathbf{g}$ to tackle these challenging problems with $f$ as t…

Cited by 18 Source ↗PDF ↗code ↗Scholar ↗

2023

Towards Better Decision Forests: Forest Alternating Optimization

Miguel Á. Carreira-Perpiñán, Magzhan Gabidolla, Arman Zharmagambetov

CVPR 2023poster

Decision forests are among the most accurate models in machine learning. This is remarkable given that the way they are trained is highly heuristic: neither the individual trees nor the overall forest optimize any well-defined loss. While diversity mechanisms such as bagging or boosting have been un…

Cited by 8 Source ↗PDF ↗Scholar ↗

2022

Improved Representation Learning For Acoustic Event Classification Using Tree-Structured Ontology

Arman Zharmagambetov, Qingming Tang, Chieh-Chi Kao, Qin Zhang, Ming Sun, Viktor Rozgic +2

ICASSP 2022accepted

Acoustic events have a hierarchical structure analogous to a tree (or a directed acyclic graph). In this work, we propose a structure-aware semi-supervised learning framework for acoustic event classification (AEC). Our hypothesis is that the audio label structure contains useful information that is…

Cited by 0 Source ↗Scholar ↗

2022

Semi-Supervised Learning with Decision Trees: Graph Laplacian Tree Alternating Optimization

Arman Zharmagambetov, Miguel A. Carreira-Perpinan

NeurIPS 2022accept

Semi-supervised learning seeks to learn a machine learning model when only a small amount of the available data is labeled. The most widespread approach uses a graph prior, which encourages similar instances to have similar predictions. This has been very successful with models ranging from kernel m…

Cited by 14 Source ↗PDF ↗Scholar ↗

2021

Learning a Tree of Neural Nets

Arman Zharmagambetov, Miguel Á. Carreira-Perpiñán

ICASSP 2021accepted

Much of the success of deep learning is due to choosing good neural net architectures and being able to train them effectively. A type of architecture that has been long sought is one that combines decision trees and neural nets. This is straightforward if the tree makes soft decisions (i.e., an inp…

Cited by 0 Source ↗Scholar ↗

2021

Softmax Tree: An Accurate, Fast Classifier When the Number of Classes Is Large

Arman Zharmagambetov, Magzhan Gabidolla, Miguel A. Carreira-Perpinan

EMNLP 2021main

Classification problems having thousands or more classes naturally occur in NLP, for example language models or document classification. A softmax or one-vs-all classifier naturally handles many classes, but it is very slow at inference time, because every class score must be calculated to find the…

Cited by 9 Source ↗PDF ↗code ↗Scholar ↗

2020

Smaller, more accurate regression forests using tree alternating optimization

Arman Zharmagambetov, Miguel Carreira-Perpinan

ICML 2020poster

Regression forests, based on ensemble approaches such as bagging or boosting, have long been recognized as the leading off-the-shelf method for regression. However, forests rely on a greedy top-down procedure such as CART to learn each tree. We extend a recent algorithm for learning classification t…

Cited by 38 Source ↗PDF ↗Scholar ↗