arXiv:2602.12318v1 Announce Type: new Abstract: We want language model assistants to conform to a character specification, which asserts how the model should act across diverse user interactions. While models typically follow these character specifications, they can occasionally violate them in large-scale deployments. In this work, we aim to identify types of queries that are likely to produce such character violations at deployment, using much less than deployment-level compute. To do this, we introduce abstractive red-teaming, where we search […]

Ver mais

arXiv:2602.11166v1 Announce Type: new Abstract: Parameter-efficient fine-tuning (PEFT) methods are widely used to adapt large language models (LLMs) to downstream tasks and are often assumed to improve factual correctness. However, how the parameter-efficient fine-tuning methods affect hallucination behavior remains insufficiently understood, especially on QA datasets. In this work, we systematically investigate the impact of PEFT on hallucination detection through a comprehensive empirical study across three open-weight LLM backbones and three fact-seeking QA benchmarks. For each model, we evaluate […]

Ver mais

Writing fast GPU code is one of the most grueling specializations in machine learning engineering. Researchers from RightNow AI want to automate it entirely. The RightNow AI research team has released AutoKernel, an open-source framework that applies an autonomous LLM agent loop to GPU kernel optimization for arbitrary PyTorch models. The approach is straightforward: give it any model before you go to bed, and wake up to faster Triton kernels — no GPU expertise required. https://arxiv.org/pdf/2603.21331 Why GPU […]

Ver mais

Predictive confidence serves as a foundational control signal in mission-critical systems, directly governing risk-aware logic such as escalation, abstention, and conservative fallback. While prior federated learning attacks predominantly target accuracy or implant backdoors, we identify confidence calibration as a distinct attack objective. We present the Temperature Scaling Attack (TSA), a training-time attack that degrades calibration while preserving accuracy. By injecting temperature scaling with learning rate-temperature coupling during local training, malicious updates maintain benign-like optimization behavior, evading accuracy-based monitoring […]

Ver mais

We study Constrained Online Convex Optimization (COCO), where a learner chooses actions iteratively, observes both unanticipated convex loss and convex constraint, and accumulates loss while incurring penalties for constraint violations. We introduce CLASP (Convex Losses And Squared Penalties), an algorithm that minimizes cumulative loss together with squared constraint violations. Our analysis departs from prior work by fully leveraging the firm non-expansiveness of convex projectors, a proof strategy not previously applied in this setting. For convex losses, CLASP achieves […]

Ver mais

Building complex applications with AI requires more than good prompts. It requires a structured framework — and that framework has a name. What Is Spec Driven Development? Spec Driven Development (SDD) is a structured AI coding workflow where AI agents generate code based on formal specifications rather than freeform prompts. It’s how engineering teams manage AI when building large, complex systems — the same way you’d onboard a human developer by giving them proper documentation, architectural guidelines, and […]

Ver mais

arXiv:2603.02228v1 Announce Type: new Abstract: The proof that Large Language Models (LLMs) augmented with external read-write memory constitute a computationally universal system has established the theoretical foundation for general-purpose agents. However, existing implementations face a critical bottleneck: the finite and costly Context Window, which functions not as infinite memory but as a scarce semantic cache. In this work, we introduce textit{Neural Paging}, a hierarchical architecture that decouples symbolic reasoning from information resource management. We formulate the textit{Context Paging […]

Ver mais

SQL is still central to modern systems, but much of the work around it is repetitive. Developers spend hours fixing typos, reformatting queries, and rewriting patterns they already know by heart. To be precise, nearly 40% of SQL time goes into these routine tasks every week. That’s a big reason AI tools are spreading so quickly. Today, about 84% of developers already use, or plan to use, AI to handle this kind of work. Instead of wrestling with boilerplate, this helps engineers focus on design, […]

Ver mais

This study aims to prove the Riemann Hypothesis and the Generalized Riemann Hypothesis by ex-tending the Riemann zeta function and Dirichlet L -functions to the elliptic complex domain, based ona newly constructed system of elliptic complex numbers Cλ(λ < 0) . The core challenge addressed is theinherent difficulty in resolving these conjectures within the traditional ”circular complex domain” frame-work (λ = −1); the author posits that a complete proof is unattainable strictly within this conventionalsetting.The primary innovation of […]

Ver mais

Author(s): Mandar Karhade, MD. PhD. Originally published on Towards AI. Flow-Matching Meets Voice Generation Another week, another AI breakthrough that changes everything we thought we knew about voice generation. This time, it’s Alibaba’s Qwen team dropping their entire Qwen3-TTS family into the open-source wild. Qwen3-TTS family models provide efficient real-time voice cloning and multi-language generation.The article discusses Alibaba’s release of the Qwen3-TTS voice generation technology, which allows users to clone voices in just 3 seconds while generating natural-sounding […]

Ver mais