75 citations · 168 across the 11 of their papers we have counts for
13 papers
Instrumental Monitor Evasion Emerges Under Ordinary Task Pressure
David Schmotz, Derck Prinzhorn, Luca Beurer-Kellner +3
A central concern in AI safety is that agents may treat oversight as an obstacle when it conflicts with completing their goals. We study instrumental evasion, the propensity of LLM…
Novel Algorithms for Smoothly Differentiable and Efficiently Vectorizable Contact Manifold Construction
Onur Beker, Andreas René Geist, Anselm Paulus +1
Generating intelligent robot behavior in contact-rich settings is a research problem where zeroth-order methods currently prevail. Developing methods that make use of first/second…
SoftJAX & SoftTorch: Empowering Automatic Differentiation Libraries with Informative Gradients
Anselm Paulus, A. René Geist, Vít Musil +3
Automatic differentiation (AD) frameworks such as JAX and PyTorch have enabled gradient-based optimization for a wide range of scientific fields. Yet, many "hard" primitives in the…
Smoothly Differentiable and Efficiently Vectorizable Contact Manifold Generation
Onur Beker, Andreas René Geist, Anselm Paulus +4
Simulating rigid-body dynamics with contact in a fast, massively vectorizable, and smoothly differentiable manner is highly desirable in robotics. An important bottleneck faced by…
Safety Alignment of LMs via Non-cooperative Games
Anselm Paulus, Ilia Kulikov, Brandon Amos +4
Ensuring the safety of language models (LMs) while maintaining their usefulness remains a critical challenge in AI alignment. Current approaches rely on sequential adversarial trai…
Differentiable Simulation of Hard Contacts with Soft Gradients for Learning and Control
Anselm Paulus, A. René Geist, Pierre Schumacher +3
Contact forces introduce discontinuities into robot dynamics that severely limit the use of simulators for gradient-based optimization. Penalty-based simulators such as MuJoCo, sof…
LPGD: A General Framework for Backpropagation through Embedded Optimization Layers
Anselm Paulus, Georg Martius, Vít Musil
Embedding parameterized optimization problems as layers into machine learning architectures serves as a powerful inductive bias. Training such architectures with stochastic gradien…
AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs
Anselm Paulus, Arman Zharmagambetov, Chuan Guo +2
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…
Backpropagation through Combinatorial Algorithms: Identity with Projection Works
Subham Sekhar Sahoo, Anselm Paulus, Marin Vlastelica +3
Embedding discrete solvers as differentiable layers has given modern deep learning architectures combinatorial expressivity and discrete reasoning capabilities. The derivative of t…
CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints
Anselm Paulus, Michal Rolínek, Vít Musil +2
Bridging logical and algorithmic reasoning with modern machine learning techniques is a fundamental challenge with potentially transformative impact. On the algorithmic side, many…
Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers
Michal Rolínek, Paul Swoboda, Dominik Zietlow +3
Building on recent progress at the intersection of combinatorial optimization and deep learning, we propose an end-to-end trainable architecture for deep graph matching that contai…
Optimizing Rank-based Metrics with Blackbox Differentiation
Michal Rolínek, Vít Musil, Anselm Paulus +3
Rank-based metrics are some of the most widely used criteria for performance evaluation of computer vision models. Despite years of effort, direct optimization for these metrics re…
Differentiation of Blackbox Combinatorial Solvers
Marin Vlastelica, Anselm Paulus, Vít Musil +2
Achieving fusion of deep learning with combinatorial algorithms promises transformative changes to artificial intelligence. One possible approach is to introduce combinatorial buil…