Related papers: EcoScratch: Cost-Effective Multimodal Repair for S…
Performance regressions have a tremendous impact on the quality of software. One way to catch regressions before they reach production is executing performance tests before deployment, e.g., using microbenchmarks, which measure performance…
Automated Program Repair (APR) struggles with complex logic errors and silent failures. Current LLM-based APR methods are mostly static, relying on source code and basic test outputs, which fail to accurately capture complex runtime…
The idea of computational error correction has been around for over half a century. The motivation has largely been to mitigate unreliable devices, manufacturing defects or harsh environments, primarily as a mandatory measure to preserve…
High-fidelity generative video editing has seen significant quality improvements by leveraging pre-trained video foundation models. However, their computational cost is a major bottleneck, as they are often designed to inefficiently process…
Nowadays, FPGAs are integrated in high-performance computing systems, servers, or even used as accelerators in System-on-Chip (SoC) platforms. Since the execution is performed in hardware, FPGA gives much higher performance and lower energy…
The architecture of a system captures important design decisions for the system. Over time, changes in a system's implementation may lead to violations of specific design decisions. This problem is common in industry and known as…
The assessment of evaluation metrics (meta-evaluation) is crucial for determining the suitability of existing metrics in text-to-image (T2I) generation tasks. Human-based meta-evaluation is costly and time-intensive, and automated…
Evaluating whether Multimodal Large Language Models (MLLMs) genuinely reason about physical dynamics remains challenging. Most existing benchmarks rely on recognition-style protocols such as Visual Question Answering (VQA) and Violation of…
Large pre-trained language models perform remarkably well on tasks that can be done "in one pass", such as generating realistic text or synthesizing computer programs. However, they struggle with tasks that require unbounded multi-step…
The most natural method for evaluating program repair systems is to run them on bug datasets, such as Defects4J. Yet, using this evaluation technique on arbitrary real-world programs requires heavy configuration. In this paper, we propose a…
Certifying neural network robustness against adversarial examples is challenging, as formal guarantees often require solving non-convex problems. Hence, incomplete verifiers are widely used because they scale efficiently and substantially…
Automatic crack detection is a critical task that has the potential to drastically reduce labor-intensive building and road inspections currently being done manually. Recent studies in this field have significantly improved the detection…
Targeting the issues of "shortcuts" and insufficient contextual understanding in complex cross-modal reasoning of multimodal large models, this paper proposes a zero-shot multimodal reasoning component guided by human-like cognitive…
While Large Language Models (LLMs) excel at the Winograd Schema Challenge (WSC), a coreference resolution task testing common-sense reasoning through pronoun disambiguation, they struggle with instances that feature minor alterations or…
Given recent advancements of Large Language Models (LLMs), code generation tasks attract immense attention for wide application in different domains. In an effort to evaluate and select a best model to automatically remediate system…
Safety-critical scenarios are essential for training and evaluating autonomous driving (AD) systems, yet remain extremely rare in real-world driving datasets. To address this, we propose Real-world Crash Grounding (RCG), a scenario…
Although large language models (LLMs) have been largely successful in generating functionally correct programs, conditioning models to produce efficient solutions while ensuring correctness remains a challenge. Further, unreliability in…
Crash reports are vital for software maintenance since they allow the developers to be informed of the problems encountered in the mobile application. Before fixing, developers need to reproduce the crash, which is an extremely…
Iteratively refining and critiquing sketches are crucial steps to developing effective designs. We introduce Scones, a mixed-initiative, machine-learning-driven system that enables users to iteratively author sketches from text…
The dependency on the correct functioning of embedded systems is rapidly growing, mainly due to their wide range of applications, such as micro-grids, automotive device control, health care, surveillance, mobile devices, and consumer…