arXiv:2602.11250v1 Announce Type: new Abstract: Consider $n$ points generated uniformly at random in the unit square, and let $L_n$ be the length of their optimal traveling salesman tour. Beardwood, Halton, and Hammersley (1959) showed $L_n / sqrt n to beta$ almost surely as $nto infty$ for some constant $beta$. The exact value of $beta$ is unknown but estimated to be approximately $0.71$ (Applegate, Bixby, Chv’atal, Cook 2011). Beardwood et al. further showed that $0.625 leq beta leq 0.92116.$ […]

Ver mais

arXiv:2601.15408v1 Announce Type: new Abstract: Medical vision-language models can automate the generation of radiology reports but struggle with accurate visual grounding and factual consistency. Existing models often misalign textual findings with visual evidence, leading to unreliable or weakly grounded predictions. We present CURE, an error-aware curriculum learning framework that improves grounding and report quality without any additional data. CURE fine-tunes a multimodal instructional model on phrase grounding, grounded report generation, and anatomy-grounded report generation using public datasets. The […]

Ver mais

arXiv:2602.00857v1 Announce Type: new Abstract: Research on adversarial robustness in language models is currently fragmented across applications and attacks, obscuring shared vulnerabilities. In this work, we propose unifying the study of adversarial robustness in text scoring models spanning dense retrievers, rerankers, and reward models. This motivates adapting both attacks and adversarial training methods across model roles. Unlike open-ended generation, text scoring failures are directly testable: an attack succeeds when an irrelevant or rejected text outscores a relevant or […]

Ver mais

arXiv:2602.15008v1 Announce Type: cross Abstract: Diffusion models over discrete spaces have recently shown striking empirical success, yet their theoretical foundations remain incomplete. In this paper, we study the sampling efficiency of score-based discrete diffusion models under a continuous-time Markov chain (CTMC) formulation, with a focus on $tau$-leaping-based samplers. We establish sharp convergence guarantees for attaining $varepsilon$ accuracy in Kullback-Leibler (KL) divergence for both uniform and masking noising processes. For uniform discrete diffusion, we show that the $tau$-leaping algorithm […]

Ver mais

arXiv:2602.15038v1 Announce Type: new Abstract: Multilingual large language models (LLMs) are increasingly deployed in linguistically diverse regions like India, yet most interpretability tools remain tailored to English. Prior work reveals that LLMs often operate in English centric representation spaces, making cross lingual interpretability a pressing concern. We introduce Indic-TunedLens, a novel interpretability framework specifically for Indian languages that learns shared affine transformations. Unlike the standard Logit Lens, which directly decodes intermediate activations, Indic-TunedLens adjusts hidden states for each […]

Ver mais

Differentially private wireless federated learning (DPWFL) is a promising framework for protecting sensitive user data. However, foundational questions on how to precisely characterize privacy loss remain open, and existing work is further limited by convergence analyses that rely on restrictive convexity assumptions or ignore the effect of gradient clipping. To overcome these issues, we present a comprehensive analysis of privacy and convergence for DPWFL with general smooth non-convex loss objectives. Our analysis explicitly incorporates both device selection and […]

Ver mais

Byline: Matthew Kayser Artificial intelligence now operates inside the core infrastructure of modern enterprises. Models influence logistics networks, financial systems, fraud detection pipelines, and automated decision platforms. As AI workloads expand across distributed environments, the security challenge is shifting. Protecting AI systems can no longer rely solely on reactive defense. Organizations must secure the full lifecycle of these systems. Cybersecurity researcher and adjunct professor Ashok Kumar Kanagala has focused much of his work on how security architecture must […]

Ver mais