Adaptive Activation Cancellation for Hallucination Mitigation in Large Language Models
arXiv:2603.10195v1 Announce Type: new Abstract: Large Language Models frequently generate fluent but factually incorrect text. We propose Adaptive Activation Cancellation (AAC), a real-time inference-time framework that treats hallucination-associated neural activations as structured interference within the transformer residual stream, drawing an...
Cluster-Aware Attention-Based Deep Reinforcement Learning for Pickup and Delivery Problems
arXiv:2603.10053v1 Announce Type: new Abstract: The Pickup and Delivery Problem (PDP) is a fundamental and challenging variant of the Vehicle Routing Problem, characterized by tightly coupled pickup--delivery pairs, precedence constraints, and spatial layouts that often exhibit clustering. Existing deep reinforcement...
Mashup Learning: Faster Finetuning by Remixing Past Checkpoints
arXiv:2603.10156v1 Announce Type: new Abstract: Finetuning on domain-specific data is a well-established method for enhancing LLM performance on downstream tasks. Training on each dataset produces a new set of model weights, resulting in a multitude of checkpoints saved in-house or...
The Confidence Gate Theorem: When Should Ranked Decision Systems Abstain?
arXiv:2603.09947v1 Announce Type: new Abstract: Ranked decision systems -- recommenders, ad auctions, clinical triage queues -- must decide when to intervene in ranked outputs and when to abstain. We study when confidence-based abstention monotonically improves decision quality, and when it...
An Empirical Study and Theoretical Explanation on Task-Level Model-Merging Collapse
arXiv:2603.09463v1 Announce Type: new Abstract: Model merging unifies independently fine-tuned LLMs from the same base, enabling reuse and integration of parallel development efforts without retraining. However, in practice we observe that merging does not always succeed: certain combinations of task-specialist...
Enhancing Debunking Effectiveness through LLM-based Personality Adaptation
arXiv:2603.09533v1 Announce Type: new Abstract: This study proposes a novel methodology for generating personalized fake news debunking messages by prompting Large Language Models (LLMs) with persona-based inputs aligned to the Big Five personality traits: Extraversion, Agreeableness, Conscientiousness, Neuroticism, and Openness....
MultiGraSCCo: A Multilingual Anonymization Benchmark with Annotations of Personal Identifiers
arXiv:2603.08879v1 Announce Type: new Abstract: Accessing sensitive patient data for machine learning is challenging due to privacy concerns. Datasets with annotations of personally identifiable information are crucial for developing and testing anonymization systems to enable safe data sharing that complies...
Cognitively Layered Data Synthesis for Domain Adaptation of LLMs to Space Situational Awareness
arXiv:2603.09231v1 Announce Type: new Abstract: Large language models (LLMs) demonstrate exceptional performance on general-purpose tasks. however, transferring them to complex engineering domains such as space situational awareness (SSA) remains challenging owing to insufficient structural alignment with mission chains, the absence...
EPIC-EuroParl-UdS: Information-Theoretic Perspectives on Translation and Interpreting
arXiv:2603.09785v1 Announce Type: new Abstract: This paper introduces an updated and combined version of the bidirectional English-German EPIC-UdS (spoken) and EuroParl-UdS (written) corpora containing original European Parliament speeches as well as their translations and interpretations. The new version corrects metadata...
Beyond Test-Time Training: Learning to Reason via Hardware-Efficient Optimal Control
arXiv:2603.09221v1 Announce Type: new Abstract: Associative memory has long underpinned the design of sequential models. Beyond recall, humans reason by projecting future states and selecting goal-directed actions, a capability that modern language models increasingly require but do not natively encode....
Bolbosh: Script-Aware Flow Matching for Kashmiri Text-to-Speech
arXiv:2603.07513v1 Announce Type: new Abstract: Kashmiri is spoken by around 7 million people but remains critically underserved in speech technology, despite its official status and rich linguistic heritage. The lack of robust Text-to-Speech (TTS) systems limits digital accessibility and inclusive...
Switchable Activation Networks
arXiv:2603.06601v1 Announce Type: new Abstract: Deep neural networks, and more recently large-scale generative models such as large language models (LLMs) and large vision-action models (LVAs), achieve remarkable performance across diverse domains, yet their prohibitive computational cost hinders deployment in resource-constrained...
Distilling and Adapting: A Topology-Aware Framework for Zero-Shot Interaction Prediction in Multiplex Biological Networks
arXiv:2603.06618v1 Announce Type: new Abstract: Multiplex Biological Networks (MBNs), which represent multiple interaction types between entities, are crucial for understanding complex biological systems. Yet, existing methods often inadequately model multiplexity, struggle to integrate structural and sequence information, and face difficulties...
Geodesic Gradient Descent: A Generic and Learning-rate-free Optimizer on Objective Function-induced Manifolds
arXiv:2603.06651v1 Announce Type: new Abstract: Euclidean gradient descent algorithms barely capture the geometry of objective function-induced hypersurfaces and risk driving update trajectories off the hypersurfaces. Riemannian gradient descent algorithms address these issues but fail to represent complex hypersurfaces via a...
Orion: Characterizing and Programming Apple's Neural Engine for LLM Training and Inference
arXiv:2603.06728v1 Announce Type: new Abstract: Over two billion Apple devices ship with a Neural Processing Unit (NPU) - the Apple Neural Engine (ANE) - yet this accelerator remains largely unused for large language model workloads. CoreML, Apple's public ML framework,...
Don't Freeze, Don't Crash: Extending the Safe Operating Range of Neural Navigation in Dense Crowds
arXiv:2603.06729v1 Announce Type: new Abstract: Navigating safely through dense crowds requires collision avoidance that generalizes beyond the densities seen during training. Learning-based crowd navigation can break under out-of-distribution crowd sizes due to density-sensitive observation normalization and social-cost scaling, while analytical...
Offline Materials Optimization with CliqueFlowmer
arXiv:2603.06082v1 Announce Type: new Abstract: Recent advances in deep learning inspired neural network-based approaches to computational materials discovery (CMD). A plethora of problems in this field involve finding materials that optimize a target property. Nevertheless, the increasingly popular generative modeling...
PRISM: Personalized Refinement of Imitation Skills for Manipulation via Human Instructions
arXiv:2603.05574v1 Announce Type: cross Abstract: This paper presents PRISM: an instruction-conditioned refinement method for imitation policies in robotic manipulation. This approach bridges Imitation Learning (IL) and Reinforcement Learning (RL) frameworks into a seamless pipeline, such that an imitation policy on...
CBR-to-SQL: Rethinking Retrieval-based Text-to-SQL using Case-based Reasoning in the Healthcare Domain
arXiv:2603.05569v1 Announce Type: cross Abstract: Extracting insights from Electronic Health Record (EHR) databases often requires SQL expertise, creating a barrier for healthcare decision-making and research. While a promising approach is to use Large Language Models (LLMs) to translate natural language...
JAWS: Enhancing Long-term Rollout of Neural Operators via Spatially-Adaptive Jacobian Regularization
arXiv:2603.05538v1 Announce Type: cross Abstract: Data-driven surrogate models improve the efficiency of simulating continuous dynamical systems, yet their autoregressive rollouts are often limited by instability and spectral blow-up. While global regularization techniques can enforce contractive dynamics, they uniformly damp high-frequency...
Evolving Medical Imaging Agents via Experience-driven Self-skill Discovery
arXiv:2603.05860v1 Announce Type: new Abstract: Clinical image interpretation is inherently multi-step and tool-centric: clinicians iteratively combine visual evidence with patient context, quantify findings, and refine their decisions through a sequence of specialized procedures. While LLM-based agents promise to orchestrate such...
NOTAI.AI: Explainable Detection of Machine-Generated Text via Curvature and Feature Attribution
arXiv:2603.05617v1 Announce Type: new Abstract: We present NOTAI.AI, an explainable framework for machine-generated text detection that extends Fast-DetectGPT by integrating curvature-based signals with neural and stylometric features in a supervised setting. The system combines 17 interpretable features, including Conditional Probability...
MASFactory: A Graph-centric Framework for Orchestrating LLM-Based Multi-Agent Systems with Vibe Graphing
arXiv:2603.06007v1 Announce Type: new Abstract: Large language model-based (LLM-based) multi-agent systems (MAS) are increasingly used to extend agentic problem solving via role specialization and collaboration. MAS workflows can be naturally modeled as directed computation graphs, where nodes execute agents/sub-workflows and...
Bias In, Bias Out? Finding Unbiased Subnetworks in Vanilla Models
arXiv:2603.05582v1 Announce Type: new Abstract: The issue of algorithmic biases in deep learning has led to the development of various debiasing techniques, many of which perform complex training procedures or dataset manipulation. However, an intriguing question arises: is it possible...
Warm Starting State-Space Models with Automata Learning
arXiv:2603.05694v1 Announce Type: new Abstract: We prove that Moore machines can be exactly realized as state-space models (SSMs), establishing a formal correspondence between symbolic automata and these continuous machine learning architectures. These Moore-SSMs preserve both the complete symbolic structure and...
Ensemble Graph Neural Networks for Probabilistic Sea Surface Temperature Forecasting via Input Perturbations
arXiv:2603.06153v1 Announce Type: new Abstract: Accurate regional ocean forecasting requires models that are both computationally efficient and capable of representing predictive uncertainty. This work investigates ensemble learning strategies for sea surface temperature (SST) forecasting using Graph Neural Networks (GNNs), with...
Artificial Intelligence Regulation on Labour Market: Comparative Perspectives on the European Union Artificial Intelligence Act in the Indonesian Context
The New Regulation of the European Union on Artificial Intelligence: Fuzzy Ethics Diffuse into Domestic Law and Sideline International Law
Regulating computational propaganda: lessons from international law
A historical analysis of the regulation of propaganda and obligations on States to prevent its dissemination reveals competing origins of the protection (and suppression) of free expression in international law. The conflict between the ‘marketplace of ideas’ approach favoured by...
Copyright Protection for AI-Generated Works: Exploring Originality and Ownership in a Digital Landscape
Abstract This research explores AI-generated originality's impact on copyright regulations. It meticulously examines legal frameworks such as the Berne Convention, EU Copyright Law, and national legislation. Rigorously analyzing cases, including Infopaq International A/S v Danske Dagblades Forening and Levola Hengelo...