arXiv:2602.22371v1 Announce Type: new Abstract: Quadratization for partial differential equations (PDEs) is a process that transforms a nonquadratic PDE into a quadratic form by introducing auxiliary variables. This symbolic transformation has been used in diverse fields to simplify the analysis, simulation, and control of nonlinear and nonquadratic PDE models. This paper presents a rigorous definition of PDE quadratization, theoretical results for the PDE quadratization problem of spatially one-dimensional PDEs-including results on existence and complexity-and introduces QuPDE, an algorithm […]

Ver mais

arXiv:2601.22443v1 Announce Type: cross Abstract: Can a diffusion model trained on bedrooms recover human faces? Diffusion models are widely used as priors for inverse problems, but standard approaches usually assume a high-fidelity model trained on data that closely match the unknown signal. In practice, one often must use a mismatched or low-fidelity diffusion prior. Surprisingly, these weak priors often perform nearly as well as full-strength, in-domain baselines. We study when and why inverse solvers are robust to weak […]

Ver mais

In this tutorial, we explore how NVIDIA SkillSpector helps us evaluate AI skills for security risks before they are used in real-world workflows. We build a controlled corpus containing both benign and deliberately vulnerable skills, scan them through SkillSpector’s programmatic LangGraph workflow, and organize the resulting risk scores and findings with pandas. We then visualize severity and category distributions, export results in SARIF format, extend the framework with a custom analyzer, and optionally apply LLM-based semantic analysis for […]

Ver mais

The Qwen team has released three embodied AI models, grouped as Qwen-Robot-Suite. The three are Qwen-RobotManip, Qwen-RobotWorld, and Qwen-RobotNav. Each is built on a Qwen vision-language backbone and targets a different robotics problem. Qwen-RobotManip is a Vision-Language-Action model for manipulation, built on Qwen3.5-4B. Qwen-RobotWorld is a language-conditioned video world model with a 60-layer MMDiT and a frozen Qwen2.5-VL encoder. Qwen-RobotNav is a navigation model built on Qwen3-VL, available at 2B, 4B, and 8B sizes. Qwen-Robot-Suite Qwen-Robot-Suite is not […]

Ver mais

arXiv:2601.16338v1 Announce Type: new Abstract: With the growing ubiquity of multi-core architectures, concurrent systems have become essential but increasingly prone to complex issues such as data races and deadlocks. While modern issue-tracking systems facilitate the reporting of such problems, labeling concurrency-related bug reports remains a labor-intensive and error-prone task. This paper presents a linguistic-pattern-based framework for automatically identifying concurrency bug reports. We derive 58 distinct linguistic patterns from 730 manually labeled concurrency bug reports, organized across four levels: […]

Ver mais

The challenge with AI in open source security has transitioned from an AI slop tsunami into more of a … plain security report tsunami. Less slop but lots of reports. Many of them really good. I’m spending hours per day on this now. It’s intense. — Daniel Stenberg, lead developer of cURL Tags: daniel-stenberg, security, curl, generative-ai, ai, llms, ai-security-research

Ver mais

arXiv:2603.24754v1 Announce Type: new Abstract: Micro-segmentation as a core requirement of zero trust architecture (ZTA) divides networks into small security zones, called micro-segments, thereby minimizing impact of security breaches and restricting lateral movement of attackers. Existing approaches for Industrial Internet of Things (IIoT) networks often remain centralized, static, or difficult to interpret. These limitations are critical in IIoT, where devices are heterogeneous, communication behavior evolves over time, and raw data sharing across sites is often undesirable. Accordingly, we […]

Ver mais

arXiv:2604.13076v1 Announce Type: new Abstract: We investigate the robustness of value alignment via finetuning with synthetic documents, using animal compassion as a value that is both important in its own right and orthogonal to existing alignment efforts. To evaluate compassionate reasoning, we develop and publicly release the Animal Harm Benchmark (AHB), a 26-question evaluation spanning 13 ethical dimensions, publicly available as a dataset and Inspect evaluation. On the AHB, training with 3000 documents achieves 77% compared to 40% […]

Ver mais

The success of RL for LLM post-training stems from an unreasonably uninformative source: a single bit of information per rollout as binary reward or preference label. At the other extreme, distillation offers dense supervision but requires demonstrations, which are costly and difficult to scale. We study text feedback as an intermediate signal: richer than scalar rewards, yet cheaper than complete demonstrations. Textual feedback is a natural mode of human interaction and is already abundant in many real-world settings, […]

Ver mais