March 2026

arXiv:2603.03410v1 Announce Type: new Abstract: Google’s SynthID-Text, the first ever production-ready generative watermark system for large language model, designs a novel Tournament-based method that achieves the state-of-the-art detectability for identifying AI-generated texts. The system’s innovation lies in: 1) a new Tournament sampling algorithm for watermarking embedding, 2) a detection strategy based on the introduced score function (e.g., Bayesian or mean score), and 3) a unified design that supports both distortionary and non-distortionary watermarking methods. This paper presents the […]

Ver mais

arXiv:2603.03409v1 Announce Type: new Abstract: This short note describes a simple variant of the Squint algorithm of Koolen and Van Erven [2015] for the classic expert problem. Via an equally simple modification of their proof, we prove that this variant ensures a regret bound that resembles the one shown in a recent work by Freund et al. [2026] for a variant of the NormalHedge algorithm [Chaudhuri et al., 2009].

Ver mais

arXiv:2603.03407v1 Announce Type: new Abstract: Large language models (LLMs) have shown strong empirical performance across pharmacology and drug discovery tasks, yet the internal mechanisms by which they encode pharmacological knowledge remain poorly understood. In this work, we investigate how drug-group semantics are represented and retrieved within Llama-based biomedical language models using causal and probing-based interpretability methods. We apply activation patching to localize where drug-group information is stored across model layers and token positions, and complement this analysis with […]

Ver mais

arXiv:2603.03406v1 Announce Type: new Abstract: How should two language models interact to produce better code than either can alone? The conventional approach — a reasoning model plans, a code specialist implements — seems natural but fails: on HumanEval+, plan-then-code degrades performance by 2.4 percentage points versus the code specialist alone. We show that reversing the interaction changes everything. When the code specialist generates freely and the reasoning model reviews instead of plans, the same two models on the […]

Ver mais

arXiv:2603.03403v1 Announce Type: new Abstract: Confidential computing protects data in use within Trusted Execution Environments (TEEs), but current TEEs provide little support for secure communication between components. As a result, pipelines of independently developed and deployed TEEs must trust one another to avoid the leakage of sensitive information they exchange — a fragile assumption that is unrealistic for modern cloud workloads. We present Mica, a confidential computing architecture that decouples confidentiality from trust. Mica provides tenants with explicit […]

Ver mais

arXiv:2603.03402v1 Announce Type: new Abstract: Equilibrium propagation (EP) is a biologically plausible alternative to backpropagation for training neural networks. However, existing EP models use a uniform scalar time step dt, which corresponds biologically to a membrane time constant that is heterogeneous across neurons. Here, we introduce heterogeneous time steps (HTS) for EP by assigning neuron-specific time constants drawn from biologically motivated distributions. We show that HTS improves training stability while maintaining competitive task performance. These results suggest that […]

Ver mais

arXiv:2603.03398v1 Announce Type: new Abstract: Federated Learning (FL) enables collaborative training of medical AI models across hospitals without centralizing patient data. However, the exchange of model updates exposes critical vulnerabilities: gradient inversion attacks can reconstruct patient information, Byzantine clients can poison the global model, and the emph{Harvest Now, Decrypt Later} (HNDL) threat renders today’s encrypted traffic vulnerable to future quantum adversaries.We introduce textbf{ZKFL-PQ} (emph{Zero-Knowledge Federated Learning, Post-Quantum}), a three-tiered cryptographic protocol that hybridizes (i) ML-KEM (FIPS~203) for quantum-resistant […]

Ver mais

arXiv:2603.03394v1 Announce Type: new Abstract: Collaborative AI experimentation in industry and academia requires environments that support rapid trials while maintaining controlled access, organisational isolation, and traceable workflows. Although interest in AI sandboxes is increasing, practical guidance on designing and building governance-aware experimentation platforms remains limited. This work designs and operationalizes a governance-aware, multi tenant AI sandbox that supports structured experimentation and produces reusable evaluation evidence across stakeholders. The sandbox was developed in an industry and academia ecosystem using […]

Ver mais

arXiv:2603.03390v1 Announce Type: new Abstract: Understanding mobility, movement, and interaction in archaeological landscapes is essential for interpreting past human behavior, transport strategies, and spatial organization, yet such processes are difficult to reconstruct from static archaeological evidence alone. This paper presents a multi-agent-based modeling framework for simulating archaeological mobility in uneven landscapes, integrating realistic terrain reconstruction, heterogeneous agent modeling, and adaptive navigation strategies. The proposed approach combines global path planning with local dynamic adaptation, through reinforcment learning, enabling agents […]

Ver mais

arXiv:2603.03389v1 Announce Type: new Abstract: Obtaining a single-vector representation from a Large Language Model’s (LLM) token-level outputs is a critical step for nearly all sentence-level tasks. However, standard pooling methods like mean or max aggregation treat tokens as an independent set, discarding the rich relational structure captured by the model’s self-attention layers and making them susceptible to signal dilution. To address this, we introduce GLOT, a lightweight, structure-aware pooling module that reframes pooling as relational learning followed by […]

Ver mais