Related papers: INSTILLER: Towards Efficient and Realistic RTL Fuz…
Recent studies have shown that reinforcement learning with verifiable rewards (RLVR) enhances overall accuracy (pass@1) but often fails to improve capability (pass@k) of LLMs in reasoning tasks, while distillation can improve both. In this…
In many practical applications, large language models (LLMs) need to acquire new knowledge not present in their pre-training data. Efficiently leveraging this knowledge usually relies on supervised fine-tuning or retrieval-augmented…
In regression problems, the use of TSK fuzzy systems is widely extended due to the precision of the obtained models. Moreover, the use of simple linear TSK models is a good choice in many real problems due to the easy understanding of the…
Modern AI systems, especially those interacting with the physical world, increasingly require real-time performance. However, the high latency of state-of-the-art generalist models, including recent vision-language action models (VLAs),…
Program analysis and automated testing have recently become an essential part of SSDLC. Directed greybox fuzzing is one of the most popular automated testing methods that focuses on error detection in predefined code regions. However, it…
As a robust and large-scale multilingual speech recognition model, Whisper has demonstrated impressive results in many low-resource and out-of-distribution scenarios. However, its encoder-decoder structure hinders its application to…
Hardware complexity continues to strain verification resources, motivating the adoption of machine learning (ML) methods to improve debug efficiency. However, ML-assisted debugging critically depends on diverse and scalable bug datasets,…
Industrial Control Protocols (ICPs) are critical to the reliability and stability of industrial infrastructure, yet their security is fundamentally compromised by a specification-blindness bottleneck. Modern fuzzers, constrained by…
Distilled autoregressive diffusion models facilitate real-time short video synthesis but suffer from severe error accumulation during long-sequence generation. While existing Test-Time Optimization (TTO) methods prove effective for images…
The Tsetlin Machine (TM) offers high-speed inference on resource-constrained devices such as CPUs. Its logic-driven operations naturally lend themselves to parallel execution on modern CPU architectures. Motivated by this, we propose an…
Fuzzing is a widely used software security testing technique that is designed to identify vulnerabilities in systems by providing invalid or unexpected input. Continuous fuzzing systems like OSS-FUZZ have been successful in finding security…
Current language models rely on static vocabularies determined at pretraining time, which can lead to decreased performance and increased computational cost for domains underrepresented in the original vocabulary. New tokens can be added to…
Grey box fuzzing is one of the most successful methods for automatic vulnerability detection. However,conventional Grey box Fuzzers like AFL can open perform fuzzing against the whole input and spend more time on smaller seeds with lower…
While fuzzing is widely accepted as an efficient program testing technique, it is still unclear how to measure the comparative quality of different fuzzers. The current de facto quality metrics are edge coverage and the number of discovered…
Fuzzing has been studied and applied ever since the 1990s. Automated and continuous fuzzing has recently been applied also to open source software projects, including the Linux and BSD kernels. This paper concentrates on the practical…
Deploying models on target domain data subject to distribution shift requires adaptation. Test-time training (TTT) emerges as a solution to this adaptation under a realistic scenario where access to full source domain data is not available,…
Virtual distillation is an error-mitigation technique that reduces quantum-computation errors without assuming the noise type. In scenarios where the user of a quantum circuit is required to additionally employ peripherals, such as delay…
Fuzzing has achieved tremendous success in discovering bugs and vulnerabilities in various software systems. Systems under test (SUTs) that take in programming or formal language as inputs, e.g., compilers, runtime engines, constraint…
Bug triaging, the task of assigning new issues to developers, is often slow and inconsistent in large projects. We present a lightweight framework that instruction-tuned large language model (LLM) with LoRA adapters and uses…
Current LLM unlearning methods are not robust. A few steps of finetuning can revert their effects. We begin by showing that this is true even for an idealized form of unlearning: training to imitate a model that was never trained on…