Related papers: EcoScratch: Cost-Effective Multimodal Repair for S…

Code generation and understanding are critical capabilities for large language models (LLMs). Thus, most LLMs are pretrained and fine-tuned on code data. However, these datasets typically treat code as static strings and rarely exploit the…

In large-scale software systems, there are often no fully-fledged bug reports with human-written descriptions when an error occurs. In this case, developers rely on stack traces, i.e., series of function calls that led to the error. Since…

Real robots are expected to repeat the same behavior in new environments with very little new data, yet modern controllers either incur heavy per-step inference or require deployment-time fine-tuning. We propose RT-Cache, a training-free…

We introduce Cargo Scan, the first interactive program analysis tool designed to help developers audit third-party Rust code. Real systems written in Rust rely on thousands of transitive dependencies. These dependencies are as dangerous in…

In situated collaboration, speakers often use intentionally underspecified deictic commands (e.g., ``pass me \textit{that}''), whose referent becomes identifiable only by aligning speech with a brief co-speech pointing \emph{stroke}.…

With the complexity of Integrated Circuits increasing, design verification has become the most time consuming part of the ASIC design flow. Nearly 70% of the SoC design cycle is consumed by verification. The most commonly used approach to…

Error Correcting Output Codes (ECOC) is a successful technique in multi-class classification, which is a core problem in Pattern Recognition and Machine Learning. A major advantage of ECOC over other methods is that the multi- class problem…

Reliable procedural monitoring in video requires exposure to naturally occurring human errors and the recoveries that follow. In egocentric recordings, mistakes are often partially occluded by hands and revealed through subtle object state…

Many approaches to program synthesis perform a combinatorial search within a large space of programs to find one that satisfies a given specification. To tame the search space blowup, previous works introduced probabilistic and neural…

Patch robustness certification is an emerging verification approach for defending against adversarial patch attacks with provable guarantees for deep learning systems. Certified recovery techniques guarantee the prediction of the sole true…

Recovering editable CAD programs from images or 3D observations is central to AI-assisted design, but progress is difficult to measure because existing evaluations are fragmented across datasets, modalities, and metrics. We introduce…

Recent progress in automated repair of performance bugs demands realistic, executable benchmarks. However, existing C++ performance benchmarks are largely built from competitive programming submissions, and recent real-world benchmarks…

Pre-training image representations from the raw text about images enables zero-shot vision transfer to downstream tasks. Through pre-training on millions of samples collected from the internet, multimodal foundation models, such as CLIP,…

Existing dynamic vulnerability patching techniques are not well-suited for embedded devices, especially mission-critical ones such as medical equipment, as they have limited computational power and memory but uninterrupted service…

In quantitative program analysis, values are assigned to execution traces to represent a quality measure. Such analyses cover important applications, e.g. resource usage. Examining all traces is well known to be intractable and therefore…

In programming education, providing manual feedback is essential but labour-intensive, posing challenges in consistency and timeliness. We introduce ECHO, a machine learning method to automate the reuse of feedback in educational code…

Test-based automatic program repair has attracted a lot of attention in recent years. However, the test suites in practice are often too weak to guarantee correctness and existing approaches often generate a large number of incorrect…

Block-based programming environments like Scratch have become widely adopted in Computer Science Education, but the mouse-based drag-and-drop interface can challenge users with disabilities. While prior work has provided solutions…

Automatically generating scripts (i.e. sequences of key steps described in text) from video demonstrations and reasoning about the subsequent steps are crucial to the modern AI virtual assistants to guide humans to complete everyday tasks,…

To approximate sums of values in key-value data streams, sketches are widely used in databases and networking systems. They offer high-confidence approximations for any given key while ensuring low time and space overhead. While existing…