Related papers: MIO: Multiverse Debugging in the Face of Input/Out…
Large language models (LLMs) are leading significant progress in code generation. Beyond one-pass code generation, recent works further integrate unit tests and program verifiers into LLMs to iteratively refine the generated programs.…
Despite recent efforts to collect multi-task, multi-embodiment datasets, to design recipes for training Vision-Language-Action models (VLAs), and to showcase these models on different robot platforms, generalist cross-embodiment robot…
Although some previous research has found ways to find inclusivity bugs (biases in software that introduce inequities), little attention has been paid to how to go about fixing such bugs. Without a process to move from finding to fixing,…
Multimodal behavior involves multiple processing stations distributed across distant brain regions, but our understanding of how such distributed processing is coordinated in the brain is limited. Here we take a decoding approach to this…
The Visual Debugger is an IntelliJ IDEA plugin that presents debug information as an object diagram to enhance program understanding. Reflecting on our past development, we detail the lessons learned and roadblocks we have experienced while…
Large Language Models (LLMs) have demonstrated remarkable potential in debugging for various programming languages. However, the application of LLMs to Verilog debugging remains insufficiently explored. Here, we present VeriDebug, an…
Multimodal large language models (MLLMs) that think with images can interactively use tools to reason about visual inputs, but current approaches often rely on a narrow set of tools with limited real-world necessity and scalability. In this…
Dynamic symbolic execution (DSE) provides a precise means to analyze programs and it can be used to generate test cases and to detect a variety of bugs including memory vulnerabilities. However, the path explosion problem may prevent a…
Hardware/Software (HW/SW) interfaces, mostly implemented as devices and device drivers, are pervasive in various computer systems. Nowadays HW/SW interfaces typically undergo intensive testing and validation before release, but they are…
Debugging ML software (i.e., the detection, localization and fixing of faults) poses unique challenges compared to traditional software largely due to the probabilistic nature and heterogeneity of its development process. Various methods…
As large-scale models evolve, language instructions are increasingly utilized in multi-modal tasks. Due to human language habits, these instructions often contain ambiguities in real-world scenarios, necessitating the integration of visual…
Existing methods for deepfake detection aim to develop generalizable detectors. Although "generalizable" is the ultimate target once and for all, with limited training forgeries and domains, it appears idealistic to expect generalization…
Firmware fuzzing has gained attention for identifying firmware bugs. However, current approaches often directly integrate fuzzing tools for general software. General software receives input as it encounters I/O functions, but firmware input…
In this paper, we introduce MIO, a novel foundation model built on multimodal tokens, capable of understanding and generating speech, text, images, and videos in an end-to-end, autoregressive manner. While the emergence of large language…
Multi-Modal Language Models (MLLMs) have transformed artificial intelligence by combining visual and text data, making applications like image captioning, visual question answering, and multi-modal content creation possible. This ability to…
Multi-objective optimization is a crucial matter in computer systems design space exploration because real-world applications often rely on a trade-off between several objectives. Derivatives are usually not available or impractical to…
Physical experiments often involve multiple imaging representations, such as X-ray scans and microscopic images. Deep learning models have been widely used for supervised analysis in these experiments. Combining different image…
Debugging is an essential process with a large share of the development effort, being a relentless quest for offensive code through tracing, inspection and iterative running sessions. Probably every developer has been in a situation with a…
We have recently witnessed tremendous success of Machine Learning (ML) in practical applications. Computer vision, speech recognition and language translation have all seen a near human level performance. We expect, in the near future, most…
As quantum computers continue to improve in quality and scale, there is a growing need for accessible software frameworks for programming them. However, the unique behavior of quantum systems means specialized approaches, beyond traditional…