February 2026

arXiv:2602.17853v1 Announce Type: new Abstract: Class imbalance induces systematic bias in deep neural networks by imposing a skewed effective class prior. This work introduces the Neural Prior Estimator (NPE), a framework that learns feature-conditioned log-prior estimates from latent representations. NPE employs one or more Prior Estimation Modules trained jointly with the backbone via a one-way logistic loss. Under the Neural Collapse regime, NPE is analytically shown to recover the class log-prior up to an additive constant, providing a […]

Ver mais

arXiv:2602.17850v1 Announce Type: new Abstract: Conversational agents increasingly mediate everyday digital interactions, yet the effects of their communication style on user experience and task success remain unclear. Addressing this gap, we describe the results of a between-subject user study where participants interact with one of two versions of a chatbot called NAVI which assists users in an interactive map-based 2D navigation task. The two chatbot versions differ only in communication style: one is friendly and supportive, while the […]

Ver mais

arXiv:2602.17849v1 Announce Type: new Abstract: Training and serving Large Language Models (LLMs) relies heavily on parallelization and collective operations, which are frequently bottlenecked by network bandwidth. Lossless compression using e.g., Huffman codes can alleviate the issue, however, Huffman codes suffer from slow, bit-sequential decoding and high hardware complexity due to deep tree traversals. Universal codes e.g., Exponential-Golomb codes are faster to decode but do not exploit the symbol frequency distributions. To address these limitations, this paper introduces Dual […]

Ver mais

arXiv:2602.17848v1 Announce Type: new Abstract: Recent work has shown that larger language models have better predictive power for eye movement and reading time data. While even the best models under-allocate probability mass to human responses, larger models assign higher-quality estimates of next tokens and their likelihood of production in cloze data because they are less sensitive to lexical co-occurrence statistics while being better aligned semantically to human cloze responses. The results provide support for the claim that the […]

Ver mais

arXiv:2602.17846v1 Announce Type: new Abstract: Diffusion models generate high-quality samples but can also memorize training data, raising serious privacy concerns. Understanding the mechanisms governing when memorization versus generalization occurs remains an active area of research. In particular, it is unclear where along the noise schedule memorization is induced, how data geometry influences it, and how phenomena at different noise scales interact. We introduce a geometric framework that partitions the noise schedule into three regimes based on the coverage […]

Ver mais

arXiv:2602.17843v1 Announce Type: new Abstract: In this work, we design and analyze a novel, provably conditionally stable, weakly coupled partitioned scheme to solve the conjugate heat transfer (CHT) problem. We consider a model CHT problem consisting of linear advection-diffusion and heat equations, coupled at an interface through continuity of temperature and heat flux. We employ high-order summation-by-parts finite-difference operators in conjunction with simultaneous-approximation-terms (SATs) in curvilinear coordinates for spatial derivatives, combined with first- and second-order time discretizations and […]

Ver mais

arXiv:2602.17842v1 Announce Type: new Abstract: Global illicit fund flows exceed an estimated $3.1 trillion annually, with stablecoins emerging as a preferred laundering medium due to their liquidity. While decentralized protocols increasingly adopt zero-knowledge proofs to obfuscate transaction graphs, centralized stablecoins remain critical “transparent choke points” for compliance. Leveraging this persistent visibility, this study analyzes an Ethereum dataset and uses behavioral features to develop a robust AML framework. Our findings demonstrate that domain-informed tree ensemble models achieve higher Macro-F1 […]

Ver mais

arXiv:2602.17841v1 Announce Type: new Abstract: While generative artificial intelligence (generative AI) is being examined extensively, some issues it epitomizes call for more refined scrutiny and deeper contextualization. Besides the lack of nuanced understanding of art’s continuously changing character in discussions about generative AI’s cultural impact, one of the notably underexplored aspects is the conceptual and ideological substrate of AI science and industry whose attributes generative AI propagates by fostering the integration of diverse modes of AI-powered artmaking into […]

Ver mais

arXiv:2602.17838v1 Announce Type: new Abstract: As developers increasingly rely on LLM-generated code summaries for documentation, testing, and review, it is important to study whether these summaries accurately reflect what the program actually does. LLMs often produce confident descriptions of what the code looks like it should do (intent), while missing subtle edge cases or logic changes that define what it actually does (behavior). We present a mutation-based evaluation methodology that directly tests whether a summary truly matches the […]

Ver mais

arXiv:2602.17837v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in safety and security critical applications, raising concerns about their robustness to model parameter fault injection attacks. Recent studies have shown that bit-flip attacks (BFAs), which exploit computer main memory (i.e., DRAM) vulnerabilities to flip a small number of bits in model weights, can severely disrupt LLM behavior. However, existing BFA on LLM largely induce un-targeted failure or general performance degradation, offering limited control over manipulating […]

Ver mais