相关论文: SERA: Soft-Verified Efficient Repository Agents

We present ELSA, a practical solution for creating deep networks that can easily be deployed at different levels of sparsity. The core idea is to embed one or more sparse networks within a single dense network as a proper subset of the…

Edge-scale deep research agents based on small language models are attractive for real-world deployment due to their advantages in cost, latency, and privacy. In this work, we study how to train a strong small deep research agent under…

Deep reinforcement learning has over the past few years shown great potential in learning near-optimal control in complex simulated environments with little visible information. Rainbow (Q-Learning) and PPO (Policy Optimisation) have shown…

Unsourced random access (URA) has emerged as a pragmatic framework for next-generation distributed sensor networks. Within URA, concatenated coding structures are often employed to ensure that the central base station can accurately recover…

Large language models (LLMs) are increasingly used in software development, yet their tendency to generate insecure code remains a major barrier to real-world deployment. Existing secure code alignment methods often suffer from a…

In the realm of parameter-efficient fine-tuning (PEFT) methods, while options like LoRA are available, there is a persistent demand in the industry for a PEFT approach that excels in both efficiency and performance within the context of…

This paper presents VulBERTa, a deep learning approach to detect security vulnerabilities in source code. Our approach pre-trains a RoBERTa model with a custom tokenisation pipeline on real-world code from open-source C/C++ projects. The…

Modern intelligent systems researchers employ the scientific method: they form hypotheses about system behavior, and then run experiments using one or more independent variables to test their hypotheses. We present SIERRA, a novel framework…

Confidential containers protect cloud-native workloads using trusted execution environments (TEEs). However, existing Container-in-TEE designs (e.g., Confidential Containers (CoCo)) encapsulate the entire runtime within the TEE, inflating…

We present a modern scalable reinforcement learning agent called SEED (Scalable, Efficient Deep-RL). By effectively utilizing modern accelerators, we show that it is not only possible to train on millions of frames per second but also to…

The study of the classifier's design and it's usage is one of the most important machine learning areas. With the development of automatic machine learning methods, various approaches are used to build a robust classifier model. Due to some…

Parameter-Efficient Fine-Tuning (PEFT) methods, such as Low-Rank Adaptation (LoRA), have significantly reduced the number of trainable parameters needed in fine-tuning large language models (LLMs). The developments of LoRA-style adapters…

Register-Transfer Level (RTL) verification is a primary bottleneck, consuming 60-70% of development time. While Large Language Models (LLMs) show promise for RTL automation, their performance and research focus have overwhelmingly centered…

Modern software development increasingly depends on open-source libraries and third-party components, which are often encapsulated into containerized environments. While improving the development and deployment of applications, this…

Adapting Foundation Models to new domains with limited training data is challenging and computationally expensive. While prior work has demonstrated the effectiveness of using domain-specific exemplars as in-context demonstrations, we…

One of the most significant challenges in the field of software code auditing is the presence of vulnerabilities in software source code. Every year, more and more software flaws are discovered, either internally in proprietary code or…

Executable software engineering data is valuable for training SWE agents, but scaling it remains difficult for two reasons: only a small fraction of real repository changes yield verifiable, high-signal task instances, and naively building…

The integration of Reinforcement Learning (RL) and Evolutionary Algorithms (EAs) aims at simultaneously exploiting the sample efficiency as well as the diversity and robustness of the two paradigms. Recently, hybrid learning frameworks…

Vision-language-action (VLA) models enable robots to follow natural-language instructions grounded in visual observations, but the instruction channel also introduces a critical vulnerability: small textual perturbations can alter…

While large language model agents have advanced software engineering tasks, the unscalable nature of existing test-based supervision is limiting the potential improvement of data scaling. The reason is twofold: (1) building and running test…