arXiv:2602.10300v1 Announce Type: new Abstract: Researchers build scaling laws to forecast the training performance of expensive large-scale runs with larger model size N and data size D. These laws assume that other training hyperparameters are optimally chosen, which can require significant effort and, in some cases, be impossible due to external hardware constraints. To improve predictability across a broader set of hyperparameters and enable simpler tuning at scale, we propose learning a textit{Configuration-to-Performance Scaling Law} (CPL): a mapping […]

Ver mais

Prime Intellect launched verifiers 0.2.0. It previews a rewritten core, shipped under the new verifiers.v1 namespace. Modern evaluations now run coding agents with tools, compaction, and subagents. Accordingly, v1 rebuilds environments to run these agentic workloads at scale. What is verifiers v1? First, consider what verifiers is: Prime Intellect’s environment stack for agentic reinforcement learning and evaluations. Previously, an environment bundled its data, agent logic, and infrastructure together. In contrast, v1 breaks that bundle into three composable pieces. […]

Ver mais

FL has emerged as a transformative paradigm for ITS, notably camera-based Road Condition Classification (RCC). However, by enabling collaboration, FL-based RCC exposes the system to adversarial participants launching Targeted Label-Flipping Attacks (TLFAs). Malicious clients (vehicles) can relabel their local training data (e.g., from an actual uneven road to a wrong smooth road), consequently compromising global model predictions and jeopardizing transportation safety. Existing countermeasures against such poisoning attacks fail to maintain resilient model performance near the necessary attack-free levels […]

Ver mais

Cybersecurity can feel a lot like the ocean. A sense of calm on the surface, but likely something unknown is lurking underwater. Varonis Threat Labs researchers Doron Kapah and Mark Vaitsman know this reality firsthand. Most of their days involve researching how threats exfiltrate sensitive data in cloud-native environments. And knowing that AI has evolved identity management and how threats attack organizations, the duo wanted to create an Entra ID training experience that gave other security practitioners first-hand knowledge of what data exfiltration in Entra ID looks like on […]

Ver mais

The Hopfield model, originally inspired by spin-glass physics, occupies a central place at the intersection of statistical mechanics, neural networks, and modern artificial intelligence. Despite its conceptual simplicity and broad applicability — from associative memory to near-optimal solutions of combinatorial optimization problems — it is rarely integrated into standard undergraduate physics curricula. In this paper, we present the Hopfield model as a pedagogically rich framework that naturally unifies core topics from undergraduate statistical physics, dynamical systems, linear algebra, […]

Ver mais

Large language models (LLMs) have transformed how we interact with AI, but one size doesn’t fit at all. Out-of-the-box LLMs are trained with broad, general knowledge and improved for a wide range of use cases, but they often fall short when it comes to domain-specific tasks, proprietary workflows, or unique business requirements. Enterprise customers increasingly need specialized LLMs that deeply understand their proprietary data, business processes, and domain-specific terminology. Without customization, you’re forced to choose between accepting generic […]

Ver mais

arXiv:2601.14445v1 Announce Type: new Abstract: Background: The integration of haptic feedback into robot-assisted minimally invasive surgery (RAMIS) has long been limited by challenges in accurately rendering forces and ensuring system safety. The need for robust, high-fidelity haptic systems is critical for enhancing the precision and reliability of teleoperated surgical tools. Methods: In this study, we present a Nonlinear Impedance Matching Approach (NIMA) designed to improve force rendering by accurately modelling complex tool-tissue interactions. Based on our previously validated […]

Ver mais

Learned optimizers are powerful alternatives to hand-designed update rules like Adam, yet they have seen limited practical adoption since they often fail to meta-generalize beyond their training distribution and incur high meta-training cost. For instance, prior work, VeLO, scaled meta-training to 4,000 TPU months ($sim$10$times$ GPT-3 compute) to meta-train a general-purpose optimizer but it failed to generalize beyond 600M parameters tasks. In this work, we present a surprising finding: by crafting a simple normalized optimizer architecture and augmenting […]

Ver mais

arXiv:2601.23030v1 Announce Type: new Abstract: Inference in non-linear continuous stochastic processes on trees is challenging, particularly when observations are sparse (leaf-only) and the topology is complex. Exact smoothing via Doob’s $h$-transform is intractable for general non-linear dynamics, while particle-based methods degrade in high dimensions. We propose Neural Backward Filtering Forward Guiding (NBFFG), a unified framework for both discrete transitions and continuous diffusions. Our method constructs a variational posterior by leveraging an auxiliary linear-Gaussian process. This auxiliary process yields […]

Ver mais