100 citations · 314 across the 34 of their papers we have counts for
40 papers
LogSTOP: Temporal Scores over Prediction Sequences for Matching and Retrieval
Avishree Khare, Hideki Okamoto, Bardh Hoxha +2
Neural models such as YOLO and HuBERT can be used to detect local properties such as objects ("car") and emotions ("angry") in individual frames of videos and audio clips respectiv…
Relational Programming with Foundation Models
Ziyang Li, Jiani Huang, Jason Liu +6
Foundation models have vast potential to enable diverse AI applications. The powerful yet incomplete nature of these models has spurred a wide range of mechanisms to augment them w…
Data-Efficient Learning with Neural Programs
Alaia Solko-Breslin, Seewon Choi, Ziyang Li +4
Many computational tasks can be naturally expressed as a composition of a DNN followed by a program written in a traditional programming language or an API call to an LLM. We call…
Understanding the Effectiveness of Large Language Models in Detecting Security Vulnerabilities
Avishree Khare, Saikat Dutta, Ziyang Li +3
While automated vulnerability detection techniques have made promising progress in detecting security vulnerabilities, their scalability and applicability remain challenging. The r…
Stability Guarantees for Feature Attributions with Multiplicative Smoothing
Anton Xue, Rajeev Alur, Eric Wong
Explanation methods for machine learning models tend not to provide any formal guarantees and may not reflect the underlying decision-making process. In this work, we analyze stabi…
Policy Synthesis and Reinforcement Learning for Discounted LTL
Rajeev Alur, Osbert Bastani, Kishor Jothimurugan +3
The difficulty of manually specifying reward functions has led to an interest in using linear temporal logic (LTL) to express objectives for reinforcement learning (RL). However, L…
Robust Subtask Learning for Compositional Generalization
Kishor Jothimurugan, Steve Hsu, Osbert Bastani +1
Compositional reinforcement learning is a promising approach for training policies to perform complex long-horizon tasks. Typically, a high-level task is decomposed into a sequence…
Composing Copyless Streaming String Transducers
Rajeev Alur, Taylor Dohmen, Ashutosh Trivedi
Streaming string transducers (SSTs) implement string-to-string transformations by reading each input word in a single left-to-right pass while maintaining fragments of potential ou…
Specification-Guided Learning of Nash Equilibria with High Social Welfare
Kishor Jothimurugan, Suguman Bansal, Osbert Bastani +1
Reinforcement learning has been shown to be an effective strategy for automatically training policies for challenging control problems. Focusing on non-cooperative multi-agent syst…
Chordal Sparsity for SDP-based Neural Network Verification
Anton Xue, Lars Lindemann, Rajeev Alur
Neural networks are central to many emerging technologies, but verifying their correctness remains a major challenge. It is known that network outputs can be sensitive and fragile…
Chordal Sparsity for Lipschitz Constant Estimation of Deep Neural Networks
Anton Xue, Lars Lindemann, Alexander Robey +3
Lipschitz constants of neural networks allow for guarantees of robustness in image classification, safety in controller design, and generalizability beyond the training data. As ca…
A Framework for Transforming Specifications in Reinforcement Learning
Rajeev Alur, Suguman Bansal, Osbert Bastani +1
Reactive synthesis algorithms allow automatic construction of policies to control an environment modeled as a Markov Decision Process (MDP) that are optimal with respect to high-le…
NetRep: Automatic Repair for Network Programs
Lei Shi, Yuepeng Wang, Rajeev Alur +1
Debugging imperative network programs is a challenging task for developers because understanding various network modules and complicated data structures is typically time-consuming…
Compositional Reinforcement Learning from Logical Specifications
Kishor Jothimurugan, Suguman Bansal, Osbert Bastani +1
We study the problem of learning control policies for complex tasks given by logical specifications. Recent approaches automatically generate a reward function from a given specifi…
Stream Processing With Dependency-Guided Synchronization (Extended Version)
Konstantinos Kallas, Filip Niksic, Caleb Stanford +1
Real-time data processing applications with low latency requirements have led to the increasing popularity of stream processing systems. While such systems offer convenient APIs th…
Session-layer Attack Traffic Classification by Program Synthesis
Lei Shi, Yahui Li, Rajeev Alur +1
Writing classification rules to identify malicious network traffic is a time-consuming and error-prone task. Learning-based classification systems automatically extract such rules…
Abstract Value Iteration for Hierarchical Reinforcement Learning
Kishor Jothimurugan, Osbert Bastani, Rajeev Alur
We propose a novel hierarchical reinforcement learning framework for control with continuous state and action spaces. In our framework, the user specifies subgoal regions which are…
A Composable Specification Language for Reinforcement Learning Tasks
Kishor Jothimurugan, Rajeev Alur, Osbert Bastani
Reinforcement learning is a promising approach for learning control policies for robot tasks. However, specifying complex tasks (e.g., with multiple objectives and safety constrain…
Computer-Aided Personalized Education
Rajeev Alur, Richard Baraniuk, Rastislav Bodik +10
The shortage of people trained in STEM fields is becoming acute, and universities and colleges are straining to satisfy this demand. In the case of computer science, for instance,…
Case Study: Verifying the Safety of an Autonomous Racing Car with a Neural Network Controller
Radoslav Ivanov, Taylor J. Carpenter, James Weimer +3
This paper describes a verification case study on an autonomous racing car with a neural network (NN) controller. Although several verification approaches have been proposed over t…
SyGuS-Comp 2018: Results and Analysis
Rajeev Alur, Dana Fisman, Saswat Padhi +2
Syntax-guided synthesis (SyGuS) is the computational problem of finding an implementation that meets both a semantic constraint given by a logical formula in a background t…
REAFFIRM: Model-Based Repair of Hybrid Systems for Improving Resiliency
Luan Viet Nguyen, Gautam Mohan, James Weimer +3
Model-based design offers a promising approach for assisting developers to build reliable and secure cyber-physical systems (CPSs) in a systematic manner. In this methodology, a de…
Verisig: verifying safety properties of hybrid systems with neural network controllers
Radoslav Ivanov, James Weimer, Rajeev Alur +2
This paper presents Verisig, a hybrid system approach to verifying safety properties of closed-loop systems using neural networks as controllers. Although techniques exist for veri…
Equilibria in Quantitative Concurrent Games
Shaull Almagor, Rajeev Alur, Suguman Bansal
Synthesis of finite-state controllers from high-level specifications in multi-agent systems can be reduced to solving multi-player concurrent games over finite graphs. The complexi…