4arXiv cs.AI (Artificial Intelligence)·
KANEx framework uses Kolmogorov-Arnold Networks to ground VLM explanations for medical imaging
Researchers introduce KANEx, a framework that leverages the symbolic transparency of Kolmogorov-Arnold Networks (KANs) to produce more faithful textual and visual explanations for chest X-ray classifiers. The system includes KAN-Map, a novel heatmap method derived directly from KAN model structure rather than gradient approximations, which feeds grounded context into downstream Vision-Language Models. Benchmarked on MIMIC-CXR, KAN-based architectures with ResNet/ViT backbones show a 10% improvement in visual localization and downstream reasoning quality over baseline approaches. The work positions mathematically interpretable architectural units as a path toward clinician-trustworthy medical AI.
Related guides (2)
Related events (8)
MedFocus: Causal Visual Attribution Framework for Chest X-ray Reasoning in Large Vision-Language Models
This paper addresses the faithfulness of visual attribution methods in Large Vision-Language Models (LVLMs) applied to chest X-ray (CXR) analysis. The authors develop a causal evaluation framework using counterfactual editing to verify whether expert-annotated regions are causally responsible for model predictions, testing 11 attribution methods across six open-source LVLMs. Finding that existing attribution methods frequently fail to identify the actual visual evidence used by models, they propose MedFocus, a concept-based attribution method using unbalanced optimal transport to localize anatomical regions and measure their causal effect on outputs. MedFocus substantially outperforms prior methods and provides spatial, concept-level, and token-level attributions.
ClinFusion: Vision-centric multimodal LLM for holistic medical image understanding
Researchers introduce ClinFusion, a multimodal LLM system designed for clinical medical understanding, featuring a cascaded vision encoder architecture (Cascade Spatial-Aware Locality Fusion) that handles both 2D and native 3D medical images within a unified encoder. The system is evaluated on a new benchmark suite including MedIF-Bench and a region-of-interest-grounded report generation metric, claiming state-of-the-art results on 20 of 24 benchmarks against open-source medical MLLMs and outperforming GPT-5.2 and Gemini-3-Flash on 13 of 16 multimodal benchmarks. Blinded evaluation by board-certified radiologists confirms ClinFusion produces the highest-ranked radiology reports, and the proposed RoI-grounded metric shows the strongest correlation with expert judgment among automatic metrics tested.
LLM-augmented XAI framework with mutual feature interactions for network operations
A new arXiv paper proposes a framework combining LLMs with SHAP-based explainability, augmented by mutual feature interaction data, to generate natural language explanations for AI/ML models used in network operations. The approach is validated on an optical quality-of-transmission estimation task with human evaluators, showing 12.2% and 6.2% improvements in explanation usefulness and scope over a SHAP-only baseline, with 97.5% correctness. The work targets the gap between technical XAI outputs and actionable insights for non-specialist network operators.
Training framework reduces calibration error 60%+ in Medical VQA multimodal LLMs
A new arXiv preprint proposes a finetuning framework to improve verbalized uncertainty calibration in multimodal LLMs applied to Medical Visual Question Answering. The composite loss function combines Brier-style calibration, anchor regularization, contrastive image-text alignment, and KL-based stabilization, evaluated on MedGemma 4B IT and Qwen2-VL 7B Instruct across three medical VQA benchmarks. The method reduces calibration error by 60% or more and improves discrimination by 26% or more while preserving predictive accuracy, outperforming prompting-, sampling-, and training-based baselines.
PG-KINN: Petrov-Galerkin formulation for Kolmogorov-Arnold Networks applied to forward and inverse PDEs
Researchers propose PG-KINN, a physics-informed neural network that combines Kolmogorov-Arnold Networks (KANs) as the trial space with an independent piecewise-polynomial test space under a Petrov-Galerkin weak formulation. The approach uses integration by parts and Gauss-Legendre quadrature to reduce differentiation order and improve conditioning, enabling application to non-self-adjoint, nonlinear, and inverse problems where energy-form methods fail. On benchmarks including crack singularities, hyperelasticity, and inverse parameter identification, PG-KINN outperforms both MLP-based physics-informed networks and KAN-based strong/energy-form alternatives (PIKAN).
RECAP: Decodability supervision for verifiable neural activation explanations
A new arXiv paper identifies a fundamental flaw in natural-language autoencoder-based explanation methods for neural activations: high reconstruction scores do not certify individual factual claims, and the standard training recipe produces co-adapted private codes (false wordings that reconstruct well) in all tested runs. The authors introduce two audit protocols and RECAP (Readable Encodings via Co-trained Auxiliary Predictors), which trains linear probe heads alongside the target model to keep designated content independently decodable. On RECAP-trained models, fresh verbalizers state designated content truthfully and private codes vanish, with probes achieving AUC 0.96 for distinguishing true from false claims—and remaining robust (AUC 0.95) against adversarial explanation edits that collapse control probes to chance. The work has direct implications for mechanistic interpretability and AI safety, as it challenges a widely-used faithfulness test and proposes a more verifiable alternative.
Retrospective analysis of multimodal VQA systems for clinical GI endoscopy reveals evaluation gaps
A new arXiv paper analyzes nine documented systems from the MediaEval Medico 2025 challenge for GI endoscopy visual question answering, examining design choices around parameter-efficient adaptation, structured reasoning, and explanation quality. The authors find that leaderboard performance gains do not reliably translate to faithful clinical reasoning, while methods enforcing structured reasoning and explicit grounding show more consistent behavior. The paper argues for evaluation frameworks that go beyond lexical overlap, incorporating evidence-linked explanations, leakage-aware data governance, and calibration checks for trustworthy healthcare AI.
Latent World Recovery: multimodal learning framework for missing modalities in bioscience
A new arXiv preprint introduces Latent World Recovery (LWR), a framework for multimodal learning when some modalities are unavailable at training or inference time. LWR aligns modality-specific embeddings in a shared latent space and fuses only available modalities, avoiding explicit reconstruction of missing ones. The approach is evaluated on incomplete multi-omics benchmarks for cancer phenotype classification and survival prediction, demonstrating robustness under partial observation.