The paper presents an AI‑powered triaging agent for banks that uses large language models to conduct multi‑turn conversations, ask relevant questions, and classify customer cases for accurate routing to specialist teams. The system is integrated with policy, safety guardrails, and reasoning frameworks, and its performance is evaluated using synthetic digital twins that simulate realistic, labeled dialogues based on historical data. Results show a 30.6% increase in classification accuracy and high satisfaction from subject‑matter experts, demonstrating the effectiveness of targeted probing for scalable banking operations.
By Alankar Atreya, Stefan Sylvius Wagner, Devesh Batra, Robert Hankache, Cristovao Iglesias Jr, Patrick Sinclair, Giulio Pelosio, Michael McMillan, Greig A. Cowan, Raad Khraishi
PR‑Smoother is an amortized smoothing method that preserves the explicit use of a prescribed simulator in both the evidence lower bound and the variational family. It learns only future‑conditioned corrections to the simulator’s rollout, yielding a non‑Gaussian smoothing distribution that can jointly infer state, parameters, and sensor bias from observations alone. The approach recovers the exact smoother in deterministic and linear‑Gaussian limits and has been shown to capture multimodal posteriors in Lorenz‑96 and scale to 16,384‑dimensional Kolmogorov flow.
By Yuta Tarumi
CORE-STACK+ is a new meta‑learning framework for deep stacked generalization that tackles two key problems in heterogeneous vision ensembles: prediction‑space multicollinearity and calibration collapse. It introduces a four‑step preconditioning pipeline—kernelized redundancy filtering, a lightweight differentiable meta‑feature gate, a spectrum‑adaptive ridge penalty, and a Laplace‑approximate Bayesian blender—to jointly improve conditioning and calibration. Across six vision benchmarks, CORE‑STACK+ boosts accuracy, reduces model count and inference cost, and significantly lowers expected calibration error compared to existing methods.
By Noor Islam S. Mohammad
The paper introduces FAPE, a four‑stage framework for evaluating the post‑processing fairness intervention ThresholdOptimizer across eight diverse domains, including criminal justice, finance, healthcare, and education. It reports that the intervention reduces disparity in most high‑disparity cases but can worsen fairness when baseline disparities are low, and that a single deployment‑time audit is unreliable without continuous monitoring and baseline‑disparity screening.
By Nithin Raghava Ramachandra Narla
The paper introduces a method for learning risk scores that remain reliable even when historical data contain unobserved confounders. By treating propensity weights as uncertain and applying sensitivity analysis with Wasserstein distributionally robust optimization, the authors formulate a robust learning problem solvable via an exponential cone program. Experiments on semi‑synthetic UCI data show the approach improves calibration by up to 29.2% over traditional benchmarks and 11.1% over the state of the art, without harming other performance metrics.
By Ryan Edmonds, Yingxiao Ye, Sina Aghaei, Andr\'es G\'omez, \c{C}a\u{g}{\i}l Ko\c{c}yi\u{g}it, Phebe Vayanos
The paper investigates the Platonic Representation Hypothesis, which posits that more capable models converge toward shared representations. By distinguishing relational structure (which samples are related) from metric geometry (quantitative relations like distances), the authors develop a controlled $2 imes2$ framework to evaluate both aspects at local and global scales. Their findings show that relational structure consistently converges across vision‑language and video‑text models, while metric geometry converges much more weakly, a pattern that persists even when using a Riemannian metric approximation.
By Junwon You, Mihyun Jang, Sangwoo Mo, Jae-Hun Jung
The paper introduces ROOSTER, a shared relative‑alignment module that learns how to map a condition sequence to a target sequence for both PPG‑to‑vital‑sign reconstruction and long‑horizon multivariate time‑series forecasting. ROOSTER uses a learnable periodic‑comb bias over the target‑condition offset, allowing it to discover identity alignment or seasonal lags and report the chosen correspondence. Experiments show that ROOSTER outperforms existing baselines on heart‑rate and respiratory‑rate reconstruction from wrist‑worn photoplethysmograms, and achieves the lowest horizon‑averaged MSE on four forecasting benchmarks, outperforming the underlying forecasting model in most dataset‑horizon settings.
By Ragamayi Puli, Shunya Nagashima
VCMM: Variance-Calibrated Momentum for Multimodal Learning proposes a new optimizer that adapts momentum based on modality-specific gradient dynamics. It estimates minibatch noise and temporal drift online, using a Kalman-inspired controller to set modality-specific momentum and applies bias correction for the first moment. Experiments on four multimodal benchmarks show consistent improvements with modest training overhead.
By Zhongjing Gu, Chenyang Huang, Yufa Feng, Chong He, Qinxu Ding, Yiming Cui
arXiv:2609. 27860v1 Announce Type: new Abstract: A pointwise-unbiased one-bit compressor reconstructs every real input in expectation while transmitting one bit.
By Tao Jiang, Minbo Gao, Shaowei Cai
The paper investigates minimal‑norm interpolation and λ2‑regularized logistic‑loss minimization for binary classification using univariate two‑layer ReLU networks. It provides exact geometric characterizations of optimal classifiers, showing that unpenalized hidden‑layer biases yield continuous piecewise‑affine functions that tightly follow label switches, while penalized biases produce a unique, sparsest classifier with a single kink per same‑label segment. Adding a free affine skip connection does not change these function‑space solutions but guarantees that every KKT point becomes globally optimal, eliminating suboptimal KKT points that can arise without the skip connection.
By Karolina Drabik, Ben Lewis, Antoni Puch, Etienne Boursier, Piotr Hofman, Matthias Englert, Ranko Lazi\'c
The study investigates whether sensory-aligned receptive fields provide computational benefits beyond mere resource efficiency in recurrent networks of Expressive Leaky Memory neurons. Across auditory and event-based visual classification tasks, receptive fields aligned with task-relevant sensory coordinates improve test accuracy compared to budget-matched random fields, but this advantage disappears when coordinates are scrambled or irrelevant. The benefit diminishes as neuronal expressivity increases, and generic synaptic sparsity regularization only partially recovers performance, indicating that structured receptive fields act as a computational prior beyond sparsity alone.
By Agnese Adorante, Aaron Spieler, Anna Levina
The paper presents a dual‑matrix computational framework that quantifies morphological and theological differences among 196 Hindu and Vajrayana Buddhist esoteric deities. It uses a Gower distance matrix with a new Cardinality Weighting algorithm for physical form and dense vector embeddings from LLMs for theological function, revealing how visual forms can mask shared functions and how high‑cardinality symbols cluster orthodox and Tantric entities. The study demonstrates near‑identical coordinates for the Hindu Chinnamasta and Buddhist Chinnamunda, and releases the architecture as an open‑source tool for Digital Humanities research.
By Ankit Bhattacharjee
arXiv:2609.28439v1 Announce Type: new
Abstract: The adoption of CMOS sensors in mobile photography is frequently compromised by the rolling shutter (RS) effect, which introduces geometric distortions...
By Xiang Ji, Guixu Lin, Jiancheng Zhao, Zhengwei Yin, Yinqiang Zheng
arXiv:2609.27222v1 Announce Type: cross
Abstract: Pneumonia is difficult to diagnose in older long-term care residents; multimorbidity and atypical presentations obscure signs, motivating operational...
By Nicholas Rasmussen, Oleg Zaslavsky, Zih-Ling Wang, Hongyu Yu, Joelle Fathi, Kaibao Nie, Amil Khanzada, Tomoko Ito
The paper introduces Safety Nudges, a browser-based tool that displays lightweight, in situ flags when a conversational AI exhibits risky behavior such as hallucination or overconfidence. In a two‑week field study with 45 frequent chatbot users, participants reported that the nudges were useful, clear, and minimally disruptive, and most felt more aware of potential AI harms. However, increased awareness did not automatically translate into measurable changes in user behavior, underscoring the need for relevance, calibration, and user control in nudge design.
By Varshini Elangovan, James Wedgwood, Chhavi Yadav, William Agnew, Sauvik Das, Virginia Smith
arXiv:2609.27455v1 Announce Type: new
Abstract: World Action Models (WAMs) jointly model action generation and environment dynamics and are mostly built on pretrained Video Diffusion Models (VDMs). I...
By Xueji Fang, Boqiang Duan, Hua Wu, Jingdong Wang, Guo-Jun Qi
arXiv:2609.27658v1 Announce Type: new
Abstract: Private decentralized learning is affected by sampling noise, privacy noise, and decentralized bias under heterogeneous data. We propose Private Recurs...
By Yizhao Fan, Wenjian Luo, Jiaojiao Zhang
arXiv:2609.27667v1 Announce Type: new
Abstract: Reinforcement learning (RL) achieves strong performance in sequential decision-making but remains brittle under dynamic uncertainty and distributional...
By Jiaxi Wu, Tiantian Zhang, Yuxing Wang, Yongzhe Chang, Xueqian Wang
arXiv:2609.26986v1 Announce Type: new
Abstract: For multimodal large language models, when images or speech conflict with accompanying text, measured text reliance can entangle modality preference wi...
By Zhuoyun Li, Boxuan Wang, Xiaowei Huang, Yi Dong
arXiv:2609.27333v1 Announce Type: new
Abstract: Platform operators increasingly rely on system prompts and fine-tuning to govern model behavior, yet it remains unclear how reliably these intervention...
By Renata Barreto, Markelle Roesti, Mohammad Tahaei