arXiv:2604.03588v1 Announce Type: new Abstract: AI agents operating over extended time horizons accumulate experiences that serve multiple concurrent goals, and must often maintain conflicting interpretations of the same events. A concession during a client negotiation encodes as a “trust-building investment” for one strategic goal and a “contractual liability” for another. Current memory architectures assume a […]
Focus Matters: Phase-Aware Suppression for Hallucination in Vision-Language Models
arXiv:2604.03556v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have achieved impressive progress in multimodal reasoning, yet they remain prone to object hallucinations, generating descriptions of objects that are not present in the input image. Recent approaches attempt to mitigate hallucinations by suppressing unreliable visual signals in the vision encoder, but many rely on iterative […]
Scaling the Scaling Logic: Agentic Meta-Synthesis of Logic Reasoning
arXiv:2602.13218v2 Announce Type: replace Abstract: Reinforcement Learning from Verifiable Rewards (RLVR) is bottlenecked by data: existing synthesis pipelines rely on expert-written code or fixed templates, confining growth to instance-level perturbations. We shift the evolvable unit from problem instances to task-family specifications. SSLogic is an agentic meta-synthesis framework in which LLM agents iteratively author and refine […]
Neural Global Optimization via Iterative Refinement from Noisy Samples
arXiv:2604.03614v1 Announce Type: cross Abstract: Global optimization of black-box functions from noisy samples is a fundamental challenge in machine learning and scientific computing. Traditional methods such as Bayesian Optimization often converge to local minima on multi-modal functions, while gradient-free methods require many function evaluations. We present a novel neural approach that learns to find global […]
Entropy and Attention Dynamics in Small Language Models: A Trace-Level Structural Analysis on the TruthfulQA Benchmark
arXiv:2604.03589v1 Announce Type: new Abstract: Small language models (SLMs) have been increasingly deployed in edge devices and other resource-constrained settings. However, these models make confident mispredictions and produce unstable output, making them risky for factual and decision-critical tasks. Current evaluation methodology relies on final accuracy or hallucination rates without explaining how internal model behavior affects […]
A Generative Foundation Model for Multimodal Histopathology
arXiv:2604.03635v1 Announce Type: cross Abstract: Accurate diagnosis and treatment of complex diseases require integrating histological, molecular, and clinical data, yet in practice these modalities are often incomplete owing to tissue scarcity, assay cost, and workflow constraints. Existing computational approaches attempt to impute missing modalities from available data but rely on task-specific models trained on narrow, […]
Domain-constrained knowledge representation: A modal framework
arXiv:2604.01770v2 Announce Type: replace Abstract: Knowledge graphs store large numbers of relations efficiently, but they remain weak at representing a quieter difficulty: the meaning of a concept often shifts with the domain in which it is used. A triple such as Apple, instance-of, Company may be acceptable in one setting while being misleading or unusable […]
AI Appeals Processor: A Deep Learning Approach to Automated Classification of Citizen Appeals in Government Services
arXiv:2604.03672v1 Announce Type: cross Abstract: Government agencies worldwide face growing volumes of citizen appeals, with electronic submissions increasing significantly over recent years. Traditional manual processing averages 20 minutes per appeal with only 67% classification accuracy, creating significant bottlenecks in public service delivery. This paper presents AI Appeals Processor, a microservice-based system that integrates natural language […]
A Multimodal Foundation Model of Spatial Transcriptomics and Histology for Biological Discovery and Clinical Prediction
arXiv:2604.03630v1 Announce Type: new Abstract: Spatial transcriptomics (ST) enables gene expression mapping within anatomical context but remains costly and low-throughput. Hematoxylin and eosin (H&E) staining offers rich morphology yet lacks molecular resolution. We present textbfours (textbfSpatial textbfTranscriptomics and histtextbfOlogy textbfRepresentation textbfModel), a foundation model trained on 1.2 million spatially resolved transcriptomic profiles with matched histology […]
RDEx-CMOP: Feasibility-Aware Indicator-Guided Differential Evolution for Fixed-Budget Constrained Multiobjective Optimization
arXiv:2604.03708v1 Announce Type: cross Abstract: Constrained multiobjective optimisation requires fast feasibility attainment together with stable convergence and diversity preservation under strict evaluation budgets. This report documents RDEx-CMOP, the differential evolution variant used in the IEEE CEC 2025 numerical optimisation competition (C06 special session) constrained multiobjective track. RDEx-CMOP integrates an epsilon-level feasibility schedule, a SPEA2-style indicator-driven […]
Causality-Based Scores Alignment in Explainable Data Management
arXiv:2503.14469v5 Announce Type: replace-cross Abstract: Different attribution scores have been proposed to quantify the relevance of database tuples for query answering in databases; e.g. Causal Responsibility, the Shapley Value, the Banzhaf Power-Index, and the Causal Effect. They have been analyzed in isolation. This work is a first investigation of score alignment depending on the query […]
Testing the Limits of Truth Directions in LLMs
arXiv:2604.03754v1 Announce Type: cross Abstract: Large language models (LLMs) have been shown to encode truth of statements in their activation space along a linear truth direction. Previous studies have argued that these directions are universal in certain aspects, while more recent work has questioned this conclusion drawing on limited generalization across some settings. In this […]