TrustFormer is a task‑specific framework that evaluates trust across multiple dimensions in dynamic collaborative systems. It synchronizes heterogeneous trust data using task identifiers and timestamps, then applies cross‑temporal and cross‑dimensional attention to model both temporal dynamics and inter‑dimensional correlations. By combining these multi‑dimensional trust profiles, the system selects optimal collaborators and achieves a 40.8% improvement in trust evaluation accuracy over existing methods.
By Botao Zhu, Xianbin Wang
The paper introduces Trusted Multi-view learning with Unified Routing (TMUR), a method that separates view-specific evidence extraction from fusion arbitration in multi-view classification. TMUR employs view-private experts, a collaborative expert, and a unified router that assigns sample-level weights based on global context, along with soft load-balancing and diversity regularization to promote balanced and discriminative expert use. Experiments on 14 datasets show that TMUR consistently improves classification accuracy and reliability compared to 15 recent baselines.
By Yilin Zhang, Cai Xu, Haishun Chen, Ziyu Guan, Wei Zhao
The paper introduces a bidirectional Mamba-enabled model (BM) for long‑term behavioral evaluation of devices in collaborative tasks. By constructing short‑time‑slot graphs of device interactions and aggregating behavioral features, BM integrates forward and backward temporal dependencies across all intervals. Experiments show that BM outperforms baseline methods, improving the accuracy of selecting trustworthy collaborators to maximize task completion value.
By Botao Zhu, Xianbin Wang
arXiv:2609.39848v1 Announce Type: new
Abstract: Foundation models are increasingly adopted across a wide range of applications, often serving as core blocks within AI systems. Yet different foundatio...
By Mingyue Ma, Zongbo Han, Changqing Zhang, Guangyu Wang
The paper introduces a systematic benchmark for evaluating explainable methods that attribute temporal interactions in sequential recommendation systems. Using a dual-model masking metric, it assesses ten XAI techniques across CNN, Transformer, SASRec, and BERT4Rec backbones on KuaiRand and MovieLens datasets, revealing that gradient-based methods like GradientSHAP and Integrated Gradients are the most faithful and robust. It also finds that raw attention weights are unreliable, while gradient-weighted attention works better on short sequences but degrades on longer horizons, and that faithful methods capture genuine task structure rather than recency or popularity bias.
By Akash Pandey, Kanisha Shah, Addrish Roy, Dwipam Katariya, Hongyangyang Shi, Amanda Ding, Kalanand Mishra, Pranab Mohanty
arXiv:2609.39429v1 Announce Type: cross
Abstract: Uncertainty Quantification (UQ) is a key requirement for trustworthy AI in high-stakes medical image analysis. In this work, we evaluate UQ in a mult...
By Gonzalo Esteban Mosquera Rojas, Sebastian R. van der Voort, Carolin M. Pirkl, Sandeep Kaushik, Marion Smits, Stefan Klein
Foundation models are increasingly adopted across a wide range of applications, often serving as core blocks within AI systems. Yet different foundation models may encode the same input from multiple...
The paper introduces CLEAR, a lightweight, task‑agnostic post‑hoc method that enhances evidential robustness in deep learning models without retraining. CLEAR uses held‑out calibration data to map the geometry of the model’s latent space, then generates perturbation views at inference to detect latent conflict. When high conflict is found, CLEAR selectively reduces evidential strength while preserving evidence for latent‑consistent inputs, achieving significant improvements in OOD and adversarial AUROC on ImageNet→CUB and running much faster than competing methods.
By Charmaine Barker, Daniel Bethell, Simos Gerasimou
arXiv:2606. 07822v1 Announce Type: cross Abstract: As language models improve and become increasingly deployed to solve a variety of tasks, trustworthiness becomes essential.
By Nishant Subramani, Palash Goyal, Yiwen Song, Mani Malek, Yuan Xue, Tomas Pfister, Hamid Palangi
arXiv:2607. 28248v1 Announce Type: cross Abstract: The deployment of deep neural networks in safety-critical domains demands reliable estimates of predictive confidence, yet conventional architectures lack principled uncertainty quantification.
By H. Martin Gillis, Thomas Trappenberg
arXiv:2608.24372v1 Announce Type: new
Abstract: AI-generated image quality assessment (AIGIQA) requires jointly reasoning about perceptual fidelity and prompt alignment, two quality dimensions that a...
By Baoliang Chen, Qing Lin, Sijie Mai
arXiv:2606. 29484v1 Announce Type: cross Abstract: Modern deepfake detectors are rarely consumed as bare classifiers.
By Md Anas Biswas