Related papers: Racets: Faceted Execution in Racket

The execution of processes leaves traces of event data in information systems. These event data can be analyzed through process mining techniques. For traditional process mining techniques, one has to associate each event with exactly one…

Accurately retargeting facial expressions to a face mesh while enabling manipulation is a key challenge in facial animation retargeting. Recent deep-learning methods address this by encoding facial expressions into a global latent code, but…

Effect handlers allow programmers to model and compose computational effects modularly. Effect systems statically guarantee that all effects are handled. Several recent practical effect systems are based on either row polymorphism or…

Graph contrastive learning is the state-of-the-art unsupervised graph representation learning framework and has shown comparable performance with supervised approaches. However, evaluating whether the graph contrastive learning is robust to…

In an attempt to make algorithms fair, the machine learning literature has largely focused on equalizing decisions, outcomes, or error rates across race or gender groups. To illustrate, consider a hypothetical government rideshare program…

Large language models (LLMs) are increasingly deployed as economic agents in marketplaces, auctions, and bidding settings. Anticipating their behavior in any specific deployment is hard. Existing strategic-reasoning benchmarks evaluate…

Evaluation of robotic manipulation systems has largely relied on fixed benchmarks authored by a small number of experts, where task instances, constraints, and success criteria are predefined and difficult to extend. This paradigm limits…

Many solutions have been proposed to curb unexpected behavior of automation apps installed on programmable IoT platforms by enforcing safety policies at runtime. However, all prior work addresses a weaker version of the actual problem due…

Our work targets at searching feasible adversarial perturbation to attack a classifier with high-dimensional categorical inputs in a domain-agnostic setting. This is intrinsically an NP-hard knapsack problem where the exploration space…

Many real-world tasks involve a mixed-initiative setup, wherein humans and AI systems collaboratively perform a task. While significant work has been conducted towards enabling humans to specify, through language, exactly how an agent…

Randomly masking and predicting word tokens has been a successful approach in pre-training language models for a variety of downstream tasks. In this work, we observe that the same idea also applies naturally to sequential decision making,…

Advanced reasoning in LLMs on challenging domains like mathematical reasoning can be tackled using verifiable rewards based reinforced fine-tuning (ReFT). In standard ReFT frameworks, a behavior model generates multiple completions with…

In this paper, we present FaceShot, a novel training-free portrait animation framework designed to bring any character into life from any driven video without fine-tuning or retraining. We achieve this by offering precise and robust reposed…

We propose a flexible framework that can be easily customized to enforce a large variety of information flow properties. Our framework combines the ideas of secure multi-execution and map-reduce computations. The information flow property…

Modern AI agents execute real-world side effects through tool calls such as file operations, shell commands, HTTP requests, and database queries. A single unsafe action, including accidental deletion, credential exposure, or data…

Educational process data, i.e., logs of detailed student activities in computerized or online learning platforms, has the potential to offer deep insights into how students learn. One can use process data for many downstream tasks such as…

In the area of networks, a common method to enforce a security policy expressed in a high-level language is based on an ad-hoc and manual rewriting process. We argue that it is possible to build a formal link between concrete and abstract…

We present a form of algebraic reasoning for computational objects which are expressed as graphs. Edges describe the flow of data between primitive operations which are represented by vertices. These graphs have an interface made of…

Robust Policy Search is the problem of learning policies that do not degrade in performance when subject to unseen environment model parameters. It is particularly relevant for transferring policies learned in a simulation environment to…

This paper introduces language-based agent control (LBAC), a new programming model for agentic applications that brings techniques from programming languages and language-based security to the problem of agent control. In conventional…