100 citations · 387 across the 36 of their papers we have counts for
38 papers
Prompt Optimization Across Multiple Agents for Representing Diverse Human Populations
Manh Hung Nguyen, Sebastian Tschiatschek, Adish Singla
The difficulty and expense of obtaining large-scale human responses make Large Language Models (LLMs) an attractive alternative and a promising proxy for human behavior. However, p…
Synthesizing High-Quality Programming Tasks with LLM-based Expert and Student Agents
Manh Hung Nguyen, Victor-Alexandru Pădurean, Alkis Gotovos +2
Generative AI is transforming computing education by enabling the automatic generation of personalized content and feedback. We investigate its capabilities in providing high-quali…
Active Third-Person Imitation Learning
Timo Klein, Susanna Weinberger, Adish Singla +1
We consider the problem of third-person imitation learning with the additional challenge that the learner must select the perspective from which they observe the expert. In our set…
Posterior Consistency for Missing Data in Variational Autoencoders
Timur Sudak, Sebastian Tschiatschek
We consider the problem of learning Variational Autoencoders (VAEs), i.e., a type of deep generative model, from data with missing values. Such data is omnipresent in real-world ap…
Large Language Models for In-Context Student Modeling: Synthesizing Student's Behavior in Visual Programming
Manh Hung Nguyen, Sebastian Tschiatschek, Adish Singla
Student modeling is central to many educational technologies as it enables predicting future learning outcomes and designing targeted instructional strategies. However, open-ended…
Applying Interdisciplinary Frameworks to Understand Algorithmic Decision-Making
Timothée Schmude, Laura Koesten, Torsten Möller +1
We argue that explanations for "algorithmic decision-making" (ADM) systems can profit by adopting practices that are already used in the learning sciences. We shortly introduce the…
Learning Safety Constraints from Demonstrations with Unknown Rewards
David Lindner, Xin Chen, Sebastian Tschiatschek +2
We propose Convex Constraint Learning for Reinforcement Learning (CoCoRL), a novel approach for inferring shared constraints in a Constrained Markov Decision Process (CMDP) from a…
Adaptive Scaffolding in Block-Based Programming via Synthesizing New Tasks as Pop Quizzes
Ahana Ghosh, Sebastian Tschiatschek, Sam Devlin +1
Block-based programming environments are increasingly used to introduce computing concepts to beginners. However, novice students often struggle in these environments, given the co…
On the Impact of Explanations on Understanding of Algorithmic Decision-Making
Timothée Schmude, Laura Koesten, Torsten Möller +1
Ethical principles for algorithms are gaining importance as more and more stakeholders are affected by "high-risk" algorithmic decision-making (ADM) systems. Understanding how thes…
Interactively Learning Preference Constraints in Linear Bandits
David Lindner, Sebastian Tschiatschek, Katja Hofmann +1
We study sequential decision-making with known rewards and unknown constraints, motivated by situations where the constraints represent expensive-to-evaluate human preferences, suc…
Equity and Fairness of Bayesian Knowledge Tracing
Sebastian Tschiatschek, Maria Knobelsdorf, Adish Singla
We consider the equity and fairness of curricula derived from Knowledge Tracing models. We begin by defining a unifying notion of an equitable tutoring system as a system that achi…
Option Transfer and SMDP Abstraction with Successor Features
Dongge Han, Sebastian Tschiatschek
Abstraction plays an important role in the generalisation of knowledge and skills and is key to sample efficient learning. In this work, we study joint temporal and state abstracti…
Contextual HyperNetworks for Novel Feature Adaptation
Angus Lamb, Evgeny Saveliev, Yingzhen Li +7
While deep learning has obtained state-of-the-art results in many applications, the adaptation of neural network architectures to incorporate new output features remains a challeng…
Information Directed Reward Learning for Reinforcement Learning
David Lindner, Matteo Turchetta, Sebastian Tschiatschek +2
For many reinforcement learning (RL) applications, specifying a reward is difficult. This paper considers an RL setting where the agent obtains information about the reward only by…
Reinforcement Learning with Efficient Active Feature Acquisition
Haiyan Yin, Yingzhen Li, Sinno Jialin Pan +2
Solving real-life sequential decision making problems under partial observability involves an exploration-exploitation problem. To be successful, an agent needs to efficiently gath…
VAEM: a Deep Generative Model for Heterogeneous Mixed Type Data
Chao Ma, Sebastian Tschiatschek, José Miguel Hernández-Lobato +2
Deep generative models often perform poorly in real-world applications due to the heterogeneity of natural data sets. Heterogeneity arises from data containing different types of f…
Replication-Robust Payoff-Allocation for Machine Learning Data Markets
Dongge Han, Michael Wooldridge, Alex Rogers +2
Submodular functions have been a powerful mathematical model for a wide range of real-world applications. Recently, submodular functions are becoming increasingly important in mach…
Educational Question Mining At Scale: Prediction, Analysis and Personalization
Zichao Wang, Sebastian Tschiatschek, Simon Woodhead +4
Online education platforms enable teachers to share a large number of educational resources such as questions to form exercises and quizzes for students. With large volumes of avai…
Resource-Efficient Neural Networks for Embedded Systems
Wolfgang Roth, Günther Schindler, Bernhard Klein +5
While machine learning is traditionally a resource intensive task, embedded systems, autonomous navigation, and the vision of the Internet of Things fuel the interest in resource-e…
Collaborative Machine Learning Markets with Data-Replication-Robust Payments
Olga Ohrimenko, Shruti Tople, Sebastian Tschiatschek
We study the problem of collaborative machine learning markets where multiple parties can achieve improved performance on their machine learning tasks by combining their training d…
Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck
Maximilian Igl, Kamil Ciosek, Yingzhen Li +4
The ability for policies to generalize to new environments is key to the broad application of RL agents. A promising approach to prevent an agent's policy from overfitting to a lim…
Towards Deployment of Robust AI Agents for Human-Machine Partnerships
Ahana Ghosh, Sebastian Tschiatschek, Hamed Mahdavi +1
We study the problem of designing AI agents that can robustly cooperate with people in human-machine partnerships. Our work is inspired by real-life scenarios in which an AI agent,…
Icebreaker: Element-wise Active Information Acquisition with Bayesian Deep Latent Gaussian Model
Wenbo Gong, Sebastian Tschiatschek, Richard Turner +3
In this paper we introduce the ice-start problem, i.e., the challenge of deploying machine learning models when only little or no training data is initially available, and acquirin…
Learner-aware Teaching: Inverse Reinforcement Learning with Preferences and Constraints
Sebastian Tschiatschek, Ahana Ghosh, Luis Haug +2
Inverse reinforcement learning (IRL) enables an agent to learn complex behavior by observing demonstrations from a (near-)optimal policy. The typical assumption is that the learner…