Related papers: The Foil: Capture-Avoiding Substitution With No Sh…
Previous deforestation and supercompilation algorithms may introduce accidental termination when applied to call-by-value programs. This hides looping bugs from the programmer, and changes the behavior of a program depending on whether it…
To efficiently execute dynamically typed languages, many language implementations have adopted a two-tier architecture. The first tier aims for low-latency startup times and collects dynamic profiles, such as the dynamic types of variables.…
Imitation learning is a proven method for creating a policy in the absence of rewards, by leveraging expert demonstrations. In this work, we apply imitation learning to conversation. In doing so, we recover a policy capable of talking to a…
Memory corruption vulnerabilities are endemic to unsafe languages, such as C, and they can even be found in safe languages that themselves are implemented in unsafe languages or linked with libraries implemented in unsafe languages. Robust…
Recently, Transformer-based encoder-decoder models have demonstrated strong performance in multilingual speech recognition. However, the decoder's autoregressive nature and large size introduce significant bottlenecks during inference.…
Exemplar-free class-incremental learning (EFCIL) aims to retain old knowledge acquired in the previous task while learning new classes, without storing the previous images due to storage constraints or privacy concerns. In EFCIL, the…
Grasping is essential in robotic manipulation, yet challenging due to object and gripper diversity and real-world complexities. Traditional analytic approaches often have long optimization times, while data-driven methods struggle with…
We present an approach to support partiality in type-level computation without compromising expressiveness or type safety. Existing frameworks for type-level computation either require totality or implicitly assume it. For example, type…
To counter software reverse engineering or tampering, software obfuscation tools can be used. However, such tools to a large degree hard-code how the obfuscations are deployed. They hence lack resilience and stealth in the face of many…
When components of a system exchange data, they need to serialise the data so that it can be sent over the network. Then, the recipient has to deserialise the data in order to be able to process it. These steps take time and have an impact…
We propose an optimization-based approach to plan power grasps. Central to our method is a reformulation of grasp planning as an infinite program under complementary constraints (IPCC), which allows contacts to happen between arbitrary…
We present an approach for implementing a formally certified loop-invariant code motion optimization by composing an unrolling pass and a formally certified yet efficient global subexpression elimination.This approach is lightweight: each…
Since its birth as a new scientific body of knowledge in the late 1950s, computer programming has become a fundamental skill needed in many other disciplines. However, programming is not easy, it is prone to errors and code re-use is key…
We introduce Compositional Imitation Learning and Execution (CompILE): a framework for learning reusable, variable-length segments of hierarchically-structured behavior from demonstration data. CompILE uses a novel unsupervised,…
An automated prepreg fabric draping system is being developed which consists of an array of actuated grippers. It has the ability to pick up a fabric ply and place it onto a double-curved mold surface. A previous research effort based on a…
AI systems can take harmful actions and are highly vulnerable to adversarial attacks. We present an approach, inspired by recent advances in representation engineering, that interrupts the models as they respond with harmful outputs with…
The goal of decompilation is to convert compiled low-level code (e.g., assembly code) back into high-level programming languages, enabling analysis in scenarios where source code is unavailable. This task supports various reverse…
Language models pretrained on large collections of tabular data have demonstrated their effectiveness in several downstream tasks. However, many of these models do not take into account the row/column permutation invariances, hierarchical…
Hardware-assisted reference monitoring is receiving increasing attention as a way to improve the security of existing software. One example is the PIPE architecture extension, which attaches metadata tags to register and memory values and…
Despite recent advances in communication and automation, regulations are still written in natural-language prose, subject to ambiguity, inconsistency, and incompleteness. How can we craft regulations with precision? Our solution is embodied…