January 2026

arXiv:2601.07901v1 Announce Type: new Abstract: Decentralized online convex optimization (D-OCO), where multiple agents within a network collaboratively learn optimal decisions in real-time, arises naturally in applications such as federated learning, sensor networks, and multi-agent control. In this paper, we study D-OCO under unknown, time-and agent-varying feedback delays. While recent work has addressed this problem (Nguyen et al., 2024), existing algorithms assume prior knowledge of the total delay over agents and still suffer from suboptimal dependence on both the […]

Ver mais

arXiv:2601.08078v1 Announce Type: new Abstract: Deep learning-based automatic medical image segmentation plays a critical role in clinical diagnosis and treatment planning but remains challenging in few-shot scenarios due to the scarcity of annotated training data. Recently, self-supervised foundation models such as DINOv3, which were trained on large natural image datasets, have shown strong potential for dense feature extraction that can help with the few-shot learning challenge. Yet, their direct application to medical images is hindered by domain differences. […]

Ver mais

arXiv:2601.08073v1 Announce Type: new Abstract: For a (possibly partial) Boolean function $fcolon{0,1}^nto{0,1}$ as well as a query complexity measure $M$ which maps Boolean functions to real numbers, define the composition limit of $M$ on $f$ by $M^*(f)=lim_{ktoinfty} M(f^k)^{1/k}$. We study the composition limits of general measures in query complexity. We show this limit converges under reasonable assumptions about the measure. We then give a surprising result regarding the composition limit of randomized query complexity: we show $R_0^*(f)=max{R^*(f),C^*(f)}$. Among […]

Ver mais

arXiv:2601.08071v1 Announce Type: new Abstract: In this short paper, we advocate for the idea that continuation-based intermediate languages correspond to intermediate logics. The goal of intermediate languages is to serve as a basis for compiler intermediate representations, allowing to represent expressive program transformations for optimisation and compilation, while preserving the properties that make programs compilable efficiently in the first place, such as the “stackability” of continuations. Intermediate logics are logics between intuitionistic and classical logic in terms of […]

Ver mais

arXiv:2601.08070v1 Announce Type: new Abstract: Negative constraints (instructions of the form “do not use word X”) represent a fundamental test of instruction-following capability in large language models. Despite their apparent simplicity, these constraints fail with striking regularity, and the conditions governing failure have remained poorly understood. This paper presents the first comprehensive mechanistic investigation of negative instruction failure. We introduce semantic pressure, a quantitative measure of the model’s intrinsic probability of generating the forbidden token, and demonstrate that […]

Ver mais

arXiv:2601.08065v1 Announce Type: new Abstract: Forward reachability analysis is the predominant approach for verifying reach-avoid properties in neural feedback systems (dynamical systems controlled by neural networks). This dominance stems from the limited scalability of existing backward reachability methods. In this work, we introduce new algorithms that compute both over- and under-approximations of backward reachable sets for such systems. We further integrate these backward algorithms with established forward analysis techniques to yield a unified verification framework for neural feedback […]

Ver mais

arXiv:2601.08064v1 Announce Type: new Abstract: Confidence estimation (CE) indicates how reliable the answers of large language models (LLMs) are, and can impact user trust and decision-making. Existing work evaluates CE methods almost exclusively through calibration, examining whether stated confidence aligns with accuracy, or discrimination, whether confidence is ranked higher for correct predictions than incorrect ones. However, these facets ignore pitfalls of CE in the context of LLMs and language variation: confidence estimates should remain consistent under semantically equivalent […]

Ver mais

arXiv:2601.08061v1 Announce Type: new Abstract: Language models now provide an interface to express and often solve general problems in natural language, yet their ultimate computational capabilities remain a major topic of scientific debate. Unlike a formal computer, a language model is trained to autoregressively predict successive elements in human-generated text. We prove that chaining a language model’s autoregressive output is sufficient to perform universal computation. That is, a language model can simulate the execution of any algorithm on […]

Ver mais

arXiv:2601.08060v1 Announce Type: new Abstract: Non-orthogonal multiple access (NOMA) is a promising technique for optical wireless communication (OWC), enabling multiple users to share the optical spectrum simultaneously through the power domain. However, the imperfection of channel state information (CSI) and residual errors in decoding process deteriorate the performance of NOMA, especially when multi-parameteric and realistic dense-user indoor scenarios are considered. In this work, we model a LiDAL-assisted RLNC-NOMA OWC system, where the light detection and localization (LiDAL) technique […]

Ver mais

arXiv:2601.08058v1 Announce Type: new Abstract: Chain-of-Thought (CoT) prompting has improved the reasoning performance of large language models (LLMs), but it remains unclear why it works and whether it is the unique mechanism for triggering reasoning in large language models. In this work, we study this question by directly analyzing and intervening on the internal representations of LLMs with Sparse Autoencoders (SAEs), identifying a small set of latent features that are causally associated with LLM reasoning behavior. Across multiple […]

Ver mais