arXiv:2604.14456v1 Announce Type: cross Abstract: Visualizing narratives is useful to writers to reflect on unfinished drafts and identify unintentional biases and inconsistencies. Literary scholars can use the visualizations to identify nuanced patterns and literary styles from written text. Current narrative visualization is limited to representing character and location co-occurrences in a timeline, omitting important and […]
Enhancing Mental Health Counseling Support in Bangladesh using Culturally-Grounded Knowledge
arXiv:2604.14576v1 Announce Type: new Abstract: Large language models (LLMs) show promise in generating supportive responses for mental health and counseling applications. However, their responses often lack cultural sensitivity, contextual grounding, and clinically appropriate guidance. This work addresses the gap of how to systematically incorporate domain-specific, clinically validated knowledge into LLMs to improve counseling quality. We […]
Preconditioned Test-Time Adaptation for Out-of-Distribution Debiasing in Narrative Generation
arXiv:2603.13683v2 Announce Type: replace-cross Abstract: Although debiased large language models (LLMs) excel at handling known or low-bias prompts, they often fail on unfamiliar and high-bias prompts. We demonstrate via out-of-distribution (OOD) detection that these high-bias prompts cause a distribution shift, degrading static model performance. To enable real-time correction, we propose CAP-TTA, a test-time adaptation framework. […]
Absolute Concentration Robustness of Non-Redundant Zero-One Networks with Conservation Laws
arXiv:2604.14592v1 Announce Type: new Abstract: Absolute concentration robustness (ACR) means the concentration of certain species stays the same in all the steady states. In this work, we study how conservation laws might effect non-vacuous ACR in reaction networks. The goal is to show whether non-vacuous ACR can be preserved or precluded by adding species that […]
FAIR Universe Weak Lensing ML Uncertainty Challenge: Handling Uncertainties and Distribution Shifts for Precision Cosmology
arXiv:2604.14451v1 Announce Type: cross Abstract: Weak gravitational lensing, the correlated distortion of background galaxy shapes by foreground structures, is a powerful probe of the matter distribution in our universe and allows accurate constraints on the cosmological model. In recent years, high-order statistics and machine learning (ML) techniques have been applied to weak lensing data to […]
El Agente Forjador: Task-Driven Agent Generation for Quantum Simulation
arXiv:2604.14609v1 Announce Type: new Abstract: AI for science promises to accelerate the discovery process. The advent of large language models (LLMs) and agentic workflows enables the expediting of a growing range of scientific tasks. However, most of the current generation of agentic systems depend on static, hand-curated toolsets that hinder adaptation to new domains and […]
MM-tau-p$^2$: Persona-Adaptive Prompting for Robust Multi-Modal Agent Evaluation in Dual-Control Settings
arXiv:2603.09643v5 Announce Type: replace-cross Abstract: Current evaluation frameworks and benchmarks for LLM powered agents focus on text chat driven agents, these frameworks do not expose the persona of user to the agent, thus operating in a user agnostic environment. Importantly, in customer experience management domain, the agent’s behaviour evolves as the agent learns about user […]
A Parallel Approach to Counting Exact Covers Based on Decomposability Property
arXiv:2604.14627v1 Announce Type: new Abstract: The exact cover problem is a classical NP-hard problem with broad applications in the area of AI. Algorithm DXZ is a method to count exact covers representing by zero-suppressed binary decision diagrams (ZBDDs). In this paper, we propose a zero-suppressed variant of decision decomposable negation normal form (in short, decision-ZDNNF), […]
Crowdsourcing of Real-world Image Annotation via Visual Properties
arXiv:2604.14449v1 Announce Type: cross Abstract: Recent advances in data-centric artificial intelligence highlight inherent limitations in object recognition datasets. One of the primary issues stems from the semantic gap problem, which results in complex many-to-many mappings between visual data and linguistic descriptions. This bias adversely affects performance in computer vision tasks. This paper proposes an image […]
Targeted Exploration via Unified Entropy Control for Reinforcement Learning
arXiv:2604.14646v1 Announce Type: new Abstract: Recent advances in reinforcement learning (RL) have improved the reasoning capabilities of large language models (LLMs) and vision-language models (VLMs). However, the widely used Group Relative Policy Optimization (GRPO) consistently suffers from entropy collapse, causing the policy to converge prematurely and lose diversity. Existing exploration methods introduce additional bias or […]
Robust Glioblastoma Segmentation and Volumetry Without T2-FLAIR: External Validation of Targeted Dropout Training
arXiv:2602.20218v3 Announce Type: replace-cross Abstract: Objectives: To externally validate targeted T2 fluid-attenuated inversion recovery (T2-FLAIR) dropout for robust automated glioblastoma segmentation and whole-tumor volumetry without T2-FLAIR, while preserving performance when the full MRI protocol is available. Methods: In this retrospective multi-dataset study, 3D nnU-Net models were developed on BraTS 2021 (n=848) and externally validated on […]
Rethinking Patient Education as Multi-turn Multi-modal Interaction
arXiv:2604.14656v1 Announce Type: new Abstract: Most medical multimodal benchmarks focus on static tasks such as image question answering, report generation, and plain-language rewriting. Patient education is more demanding: systems must identify relevant evidence across images, show patients where to look, explain findings in accessible language, and handle confusion or distress. Yet most patient education work […]