Related papers: NCCLbpf: Verified, Composable Policy Execution for…
Driven by the progress in efficient embedded processing, there is an accelerating trend toward running machine learning models directly on wearable Brain-Machine Interfaces (BMIs) to improve portability and privacy and maximize battery…
Tool-augmented Large Language Model (LLM) agents have demonstrated impressive capabilities in automating complex, multi-step real-world tasks, yet remain vulnerable to indirect prompt injection. Adversaries exploit this weakness by…
Complementary-label learning (CLL) is a weakly supervised learning paradigm for multiclass classification, where only complementary labels -- indicating classes an instance does not belong to -- are provided to the learning algorithm.…
We develop an optimization-free framework for safe stabilization of single-input control-affine nonlinear systems with a given control Lyapunov function (CLF) and a given control barrier function (CBF), where the desired equilibrium lies in…
Communication among devices in multi-GPU systems plays an important role in terms of performance and scalability. In order to optimize an application, programmers need to know the type and amount of the communication happening among GPUs.…
Model Predictive Control (MPC) is widely adopted for agile multirotor vehicles, yet achieving both stability and obstacle-free flight is particularly challenging when a payload is suspended beneath the airframe. This paper introduces a…
Multi-tenant cloud networks have various security and monitoring service functions (SFs) that constitute a service function chain (SFC) between two endpoints. SF rule ordering overlaps and policy conflicts can cause increased latency,…
Large pre-trained Vision-Language Models (VLMs), such as Contrastive Language-Image Pre-training (CLIP), have exhibited remarkable zero-shot performance across various image classification tasks. Fine-tuning these models on domain-specific…
We introduce ${\rm C{\small LEVER}}$, a high-quality, curated benchmark of 161 problems for end-to-end verified code generation in Lean. Each problem consists of (1) the task of generating a specification that matches a held-out…
With the increasing popularity of plugin-based software systems, ensuring the security of plugins has become a critical concern. When users install plugins or browse websites with plugins from an untrusted source, how can we be sure that…
Recent advancements in Quantum Neural Networks (QNNs) have demonstrated theoretical and experimental performance superior to their classical counterparts in a wide range of applications. However, existing centralized QNNs cannot solve many…
Verifying multi-step reasoning in large language models is difficult due to imprecise error localization and high token costs. Existing methods either assess entire reasoning chains, suffering attention dilution, or rely on expensive…
We present enclawed, a hard-fork hardening framework built on the OpenClaw AI assistant gateway. enclawed targets deployments that need attestable peer trust, deny-by-default external connectivity, signed-module loading, and a…
Decentralized inference provides a scalable and resilient paradigm for serving large language models (LLMs), enabling fragmented global resource utilization and reducing reliance on centralized providers. However, in a permissionless…
Training certifiably robust neural networks is an important but challenging task. While many algorithms for (deterministic) certified training have been proposed, they are often evaluated on different training schedules, certification…
This paper presents a dissipativity-based distributed droop-free control and communication topology co-design framework for voltage regulation and current sharing in DC microgrids (MGs), where constant-power loads (CPLs) and voltage-source…
Deploying trustworthy AI systems requires principled uncertainty quantification. Conformal prediction (CP) is a widely used framework for constructing prediction sets with distribution-free coverage guarantees. In many practical settings,…
Federated learning (FL) is a promising distributed learning solution that only exchanges model parameters without revealing raw data. However, the centralized architecture of FL is vulnerable to the single point of failure. In addition, FL…
Cross-domain recommendation (CDR) aims to improve recommendation accuracy in sparse domains by transferring knowledge from data-rich domains. However, existing CDR approaches often assume that user-item interaction data across domains is…
We provide a stability and performance analysis for nonlinear model predictive control (NMPC) schemes subject to input constraints. Given an exponential stabilizability and detectability condition w.r.t. the employed state cost, we provide…