January 2026

arXiv:2601.19939v1 Announce Type: new Abstract: Oculomics – the concept of predicting systemic diseases, such as cardiovascular disease and dementia, through retinal imaging – has advanced rapidly due to the data efficiency of transformer-based foundation models like RETFound. Image-level mixed sample data augmentations, such as CutMix and MixUp, are frequently used for training transformers, yet these techniques perturb patient-specific attributes, such as medical comorbidity and clinical factors, since they only account for images and labels. To address this limitation, […]

Ver mais

arXiv:2601.19938v1 Announce Type: new Abstract: Decentralized Federated Learning (DFL) is a serverless collaborative machine learning paradigm where devices collaborate directly with neighbouring devices to exchange model information for learning a generalized model. However, variations in individual experiences and different levels of device interactions lead to data and model initialization heterogeneities across devices. Such heterogeneities leave variations in local model parameters across devices that leads to slower convergence. This paper tackles the data and model heterogeneity by explicitly addressing […]

Ver mais

arXiv:2601.19936v1 Announce Type: new Abstract: The opacity of massive pretraining corpora in Large Language Models (LLMs) raises significant privacy and copyright concerns, making pretraining data detection a critical challenge. Existing state-of-the-art methods typically rely on token likelihoods, yet they often overlook the divergence from the model’s top-1 prediction and local correlation between adjacent tokens. In this work, we propose Gap-K%, a novel pretraining data detection method grounded in the optimization dynamics of LLM pretraining. By analyzing the next-token […]

Ver mais

arXiv:2601.19935v1 Announce Type: new Abstract: Large Language Model (LLM)-based agents are increasingly deployed for complex, tool-based tasks where long-term memory is critical to driving actions. Existing benchmarks, however, primarily test a angent’s ability to passively retrieve isolated facts in response to explicit questions. They fail to evaluate the more crucial capability of actively applying memory to execute tasks. To address this gap, we introduce textsc{Mem2ActBench}, a benchmark for evaluating whether agents can proactively leverage long-term memory to execute […]

Ver mais

arXiv:2601.19934v1 Announce Type: new Abstract: Large language models (LLMs) are widely used for tasks ranging from summarisation to decision support. In practice, identical prompts do not always produce identical outputs, even when temperature and other decoding parameters are fixed. In this work, we conduct repeated-run experiments to empirically quantify baseline behavioural drift, defined as output variability observed when the same prompt is issued multiple times under operator-free conditions. We evaluate two publicly accessible models, gpt-4o-mini and llama3.1-8b, across […]

Ver mais

arXiv:2601.19933v1 Announce Type: new Abstract: Non-Resolution Reasoning (NRR) provides a formal framework for maintaining semantic ambiguity rather than forcing premature interpretation collapse. While the foundational architecture establishes state spaces and operators for ambiguity-preserving computation, the critical question of how natural language maps to these mathematical structures remains open. This paper introduces the text-to-state mapping function {phi} that transforms linguistic input into superposition states within the NRR framework. We formalize the Contradiction-Preservation Principle, which requires that genuinely ambiguous expressions […]

Ver mais

arXiv:2601.19932v1 Announce Type: new Abstract: Coded language is an important part of human communication. It refers to cases where users intentionally encode meaning so that the surface text differs from the intended meaning and must be decoded to be understood. Current language models handle coded language poorly. Progress has been limited by the lack of real-world datasets and clear taxonomies. This paper introduces CodedLang, a dataset of 7,744 Chinese Google Maps reviews, including 900 reviews with span-level annotations […]

Ver mais

arXiv:2601.19931v1 Announce Type: new Abstract: We present a hybrid neuro-symbolic system for the SemEval-2026 Task 4 on Narrative Story Similarity. Our approach combines neural self-consistency voting with a novel Multi-Scale Narrative Analysis Ensemble that operates as a symbolic tiebreaker. The neural network component uses a large language model with multiple parallel votes, applying a supermajority threshold for confident decisions and escalating uncertain cases to additional voting rounds. When votes result in a perfect tie, a symbolic ensemble combining […]

Ver mais

arXiv:2601.19930v1 Announce Type: new Abstract: We introduce a new benchmark for Danish culture via cultural heritage, Daisy, based on the curated topics from the Danish Culture Canon 2006. For each artifact in the culture canon, we query the corresponding Wikipedia page and have a language model generate random questions. This yields a sampling strategy within each work, with a mix of central of peripheral questions for each work, not only knowledge of mainstream information, but also in-depth cornerstones […]

Ver mais

arXiv:2601.19929v1 Announce Type: new Abstract: We introduce Stingy Context, a hierarchical tree-based compression scheme achieving 18:1 reduction in LLM context for auto-coding tasks. Using our TREEFRAG exploit decomposition, we reduce a real source code base of 239k tokens to 11k tokens while preserving task fidelity. Empirical results across 12 Frontier models show 94 to 97% success on 40 real-world issues at low cost, outperforming flat methods and mitigating lost-in-the-middle effects.

Ver mais