arXiv:2603.06260v1 Announce Type: cross Abstract: The orienteering problem with time windows and variable profits (OPTWVP) is common in many real-world applications and involves continuous time variables. Current approaches fail to develop an efficient solver for this orienteering problem variant with discrete and continuous variables. In this paper, we propose a learning-based two-stage DEcoupled discrete-Continuous optimization […]
Longitudinal Lesion Inpainting in Brain MRI via 3D Region Aware Diffusion
arXiv:2603.05693v1 Announce Type: cross Abstract: Accurate longitudinal analysis of brain MRI is often hindered by evolving lesions, which bias automated neuroimaging pipelines. While deep generative models have shown promise in inpainting these lesions, most existing methods operate cross-sectionally or lack 3D anatomical continuity. We present a novel pseudo-3D longitudinal inpainting framework based on Denoising Diffusion […]
ESAA-Security: An Event-Sourced, Verifiable Architecture for Agent-Assisted Security Audits of AI-Generated Code
arXiv:2603.06365v1 Announce Type: cross Abstract: AI-assisted software generation has increased development speed, but it has also amplified a persistent engineering problem: systems that are functionally correct may still be structurally insecure. In practice, prompt-based security review with large language models often suffers from uneven coverage, weak reproducibility, unsupported findings, and the absence of an immutable […]
The Fragility Of Moral Judgment In Large Language Models
arXiv:2603.05651v1 Announce Type: cross Abstract: People increasingly use large language models (LLMs) for everyday moral and interpersonal guidance, yet these systems cannot interrogate missing context and judge dilemmas as presented. We introduce a perturbation framework for testing the stability and manipulability of LLM moral judgments while holding the underlying moral conflict constant. Using 2,939 dilemmas […]
Model Change for Description Logic Concepts
arXiv:2603.05562v1 Announce Type: cross Abstract: We consider the problem of modifying a description logic concept in light of models represented as pointed interpretations. We call this setting model change, and distinguish three main kinds of changes: eviction, which consists of only removing models; reception, which incorporates models; and revision, which combines removal with incorporation of […]
Tool-Genesis: A Task-Driven Tool Creation Benchmark for Self-Evolving Language Agent
arXiv:2603.05578v1 Announce Type: cross Abstract: Research on self-evolving language agents has accelerated, drawing increasing attention to their ability to create, adapt, and maintain tools from task requirements. However, existing benchmarks predominantly rely on predefined specifications, which limits scalability and hinders truly autonomous evolution. While recent studies attempt to dynamically generate tools, they primarily emphasize downstream […]
Transforming Agency. On the mode of existence of Large Language Models
arXiv:2407.10735v3 Announce Type: replace Abstract: This paper investigates the ontological characterization of Large Language Models (LLMs) like ChatGPT. Between inflationary and deflationary accounts, we pay special attention to their status as agents. This requires explaining in detail the architecture, processing, and training procedures that enable LLMs to display their capacities, and the extensions used to […]
Reasoning Models Struggle to Control their Chains of Thought
arXiv:2603.05706v1 Announce Type: new Abstract: Chain-of-thought (CoT) monitoring is a promising tool for detecting misbehaviors and understanding the motivations of modern reasoning models. However, if models can control what they verbalize in their CoT, it could undermine CoT monitorability. To measure this undesirable capability — CoT controllability — we introduce the CoT-Control evaluation suite, which […]
Conditioning LLMs to Generate Code-Switched Text
arXiv:2502.12924v3 Announce Type: replace-cross Abstract: Code-switching (CS) is still a critical challenge in Natural Language Processing (NLP), due to the limited availability of large-scale, diverse CS datasets for robust training and evaluation. Despite recent advances, the capabilities and limitations of LLMs in handling CS are still not fully understood. In this work, we investigate the […]
Prosodic Boundary-Aware Streaming Generation for LLM-Based TTS with Streaming Text Input
arXiv:2603.06444v1 Announce Type: cross Abstract: Streaming TTS that receives streaming text is essential for interactive systems, yet this scheme faces two major challenges: unnatural prosody due to missing lookahead and long-form collapse due to unbounded context. We propose a prosodic-boundary-aware post-training strategy, adapting a pretrained LLM-based TTS model using weakly time-aligned data. Specifically, the model […]
CanvasMAR: Improving Masked Autoregressive Video Prediction With Canvas
arXiv:2510.13669v2 Announce Type: replace-cross Abstract: Masked autoregressive models (MAR) have emerged as a powerful paradigm for image and video generation, combining the flexibility of masked modeling with the expressiveness of continuous tokenizers. However, when sampling individual frames, video MAR models often produce highly distorted outputs due to the lack of a structured global prior, especially […]
Iterative Quantum Feature Maps
arXiv:2506.19461v3 Announce Type: replace-cross Abstract: Quantum machine learning models that leverage quantum circuits as quantum feature maps (QFMs) are recognized for their enhanced expressive power in learning tasks. Such models have demonstrated rigorous end-to-end quantum speedups for specific families of classification problems. However, deploying deep QFMs on real quantum hardware remains challenging due to circuit […]