Search Results

Many recent prompting strategies for large language models (LLMs) query the model multiple times sequentially - first to produce intermediate results and then the final answer. However, using these methods, both decoder and model are unaware of potential ...

To ensure that text generated by large language models (LLMs) is in an expected format, constrained decoding proposes to enforce strict formal language constraints during generation. However, as we show in this work, not only do such methods incur ...

Training certifiably robust neural networks remains a notoriously hard problem. While adversarial training optimizes under-approximations of the worst-case loss, which leads to insufficient regularization for certification, sound certified training ...

While the ImageNet dataset has been driving computer vision research over the past decade, significant label noise and ambiguity have made top-1 accuracy an insufficient measure of further progress. To address this, new label-sets and evaluation ...

Graph databases (GDBs) are crucial in academic and industry applications. The key challenges in developing GDBs are achieving high performance, scalability, programmability, and portability. To tackle these challenges, we harness established practices ...

This paper investigates the accuracy of Augmented Reality (AR) technologies, particularly commercially available optical see-through displays, in depicting virtual content inside the human body for surgical planning. Their inherent limitations result in ...

Numerous irregular graph datasets, for example social networks or web graphs, may contain even trillions of edges. Often, their structure changes over time and they have domain-specific rich data associated with vertices and edges. Graph database systems ...

Large language models have demonstrated outstanding performance on a wide range of tasks such as question answering and code generation. On a high level, given an input, a language model can be used to automatically complete the sequence in a ...

We present a new abstract interpretation framework for the precise over-approximation of numerical fixpoint iterators. Our key observation is that unlike in standard abstract interpretation (AI), typically used to over-approximate all reachable ...

Graph processing has become an important part of various areas of computing, including machine learning, medical applications, social network analysis, computational sciences, and others. A growing amount of the associated graph processing workloads are <...

Tree-based models are used in many high-stakes application domains such as finance and medicine, where robustness and interpretability are of utmost importance. Yet, methods for improving and certifying their robustness are severely under-explored, in ...

Reliable neural networks (NNs) provide important inference-time reliability guarantees such as fairness and robustness. Complementarily, privacy-preserving NN inference protects the privacy of client data. So far these two emerging areas have been ...

Existing neural network verifiers compute a proof that each input is handled correctly under a given perturbation by propagating a symbolic abstraction of reachable values at each layer. This process is repeated from scratch independently for each ...

Safety-critical systems are becoming more complex with use cases like autonomous driving or human-robot collaboration. Therefore, the performance impact of software-based fault-tolerance methods is challenging. Using software-based fault tolerance ...

Reinforcement learning is a promising approach for manufacturing processes. Process knowledge can be gained automatically, and autonomous tuning of control is possible. However, the use of reinforcement learning in a production environment imposes ...

We extend randomized smoothing to cover parameterized transformations (e.g., rotations, translations) and certify robustness in the parameter space (e.g., rotation angle). This is particularly challenging as interpolation and rounding effects mean that ...

Fair representation learning provides an effective way of enforcing fairness constraints without compromising utility for downstream users. A desirable family of such fairness constraints, each requiring similar treatment for similar individuals, is ...

Developing high-performance and energy-efficient algorithms for maximum matchings is becoming increasingly important in social network analysis, computational sciences, scheduling, and others. In this work, we propose the first maximum matching ...

This paper introduces a new decision support tool to optimize advertising campaigns for new product launches based on learnings from an ex post analysis of prior campaigns.

The launch of a new product is one of the most critical activities that product and brand managers are faced with. It requires a substantial communications budget to introduce the new product to the market. As the number of media channels proliferates, ...

Developing high-performance and energy-efficient algorithms for maximum matchings is becoming increasingly important in social network analysis, computational sciences, scheduling, and others. In this work, we propose the first maximum matching ...