Related papers: REVERSIM: An Open-Source Environment for the Contr…
The human brain has immense learning capabilities at extreme energy efficiencies and scale that no artificial system has been able to match. For decades, reverse engineering the brain has been one of the top priorities of science and…
Modern architecture research relies on simulators to evaluate system security, yet analyzing emerging hardware vulnerabilities like RowHammer requires full-system visibility. As RowHammer vulnerabilities worsen with continuous technology…
To reduce the carbon footprint of computing and stabilize electricity grids, there is an increasing focus on approaches that align the power usage of IT infrastructure with the availability of clean energy. Unfortunately, research on…
Empirical risk minimization (ERM) is a cornerstone of modern machine learning (ML), supported by advances in optimization theory that ensure efficient solutions with provable algorithmic and statistical learning rates. Privacy, memory,…
Expert-level scientific reasoning remains challenging for large language models, particularly on benchmarks such as Humanity's Last Exam (HLE), where rigid tool pipelines, brittle multi-agent coordination, and inefficient test-time scaling…
Realistic and controllable simulation is critical for advancing end-to-end autonomous driving, yet existing approaches often struggle to support novel view synthesis under large viewpoint changes or to ensure geometric consistency. We…
In coming up with solutions to real-world problems, humans implicitly adhere to constraints that are too numerous and complex to be specified completely. However, reinforcement learning (RL) agents need these constraints to learn the…
In this study, we propose a new methodology to control how user's data is recognized and used by AI via exploiting the properties of adversarial examples. For this purpose, we propose reversible adversarial example (RAE), a new type of…
A promising direction for recovering the lost information in low-resolution headshot images is utilizing a set of high-resolution exemplars from the same identity. Complementary images in the reference set can improve the generated headshot…
Widespread use of memory unsafe programming languages (e.g., C and C++) leaves many systems vulnerable to memory corruption attacks. A variety of defenses have been proposed to mitigate attacks that exploit memory errors to hijack the…
AI agents are increasingly used to diagnose and mitigate failures in production systems, known as agentic Site Reliability Engineering (SRE). Current SRE benchmarks are limited to oversimplistic SRE tasks and are unfortunately hard to…
High-level synthesis (HLS) is a process that automatically translates a software program in a high-level language into a low-level hardware description. However, the hardware designs produced by HLS tools still suffer from a significant…
Machine learning inference engine is of great interest to smart edge computing. Compute-in-memory (CIM) architecture has shown significant improvements in throughput and energy efficiency for hardware acceleration. Emerging non-volatile…
Efficient learning in the environment with sparse rewards is one of the most important challenges in Deep Reinforcement Learning (DRL). In continuous DRL environments such as robotic arms control, Hindsight Experience Replay (HER) has been…
To help researchers conduct a systematic review or meta-analysis as efficiently and transparently as possible, we designed a tool (ASReview) to accelerate the step of screening titles and abstracts. For many tasks - including but not…
It is being proved that the neurochip \Totem{} is a viable solution for high quality and real time computational tasks in HEP, including event classification, triggering and signal processing. The architecture of the chip is based on a…
Intelligent assistive technologies are increasingly recognized as critical daily-use enablers for people with disabilities and age-related functional decline. Longitudinal studies, curation of quality datasets, live monitoring in activities…
Integrating research evidence into practice is one of the main goals of Evidence-Based Software Engineering (EBSE). Secondary studies, one of the main EBSE products, are intended to summarize the best research evidence and make them easily…
Human-Centric Software Engineering (HCSE) refers to the software engineering (SE) processes that put human needs and requirements as core practice throughout the software development life cycle. A large majority of software projects fail to…
Software security vulnerabilities can lead to severe consequences, making early detection essential. Although code review serves as a critical defense mechanism against security flaws, relevant feedback remains scarce due to limited…