The paper introduces DualRes, a compact oscillatory state‑space model designed for vibration‑based fault diagnosis when labeled data are scarce and computational resources are limited. DualRes integrates two spectral views of vibration and employs selective oscillatory memory to learn how long to retain temporal patterns, resulting in a lightweight encoder with only 39,528 parameters. Evaluations on six bearing datasets and a gearbox benchmark show that DualRes outperforms nine competing methods across most label budgets, achieving significant gains in macro‑F1, faster inference, and reduced storage requirements.
By Mainak Mallick, Seung-Kyum Choi
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
The paper introduces MENO, a Memory‑Efficient Neural Operator designed for solving partial differential equations (PDEs). MENO leverages a Manifold Function Encoder to achieve a small memory footprint that does not depend on data resolution, enabling faster training and potential scalability to large models. It accepts PDE inputs of arbitrary form—including different geometric domains and discretizations—allowing cross‑geometry scenarios, and demonstrates strong generalization with superior accuracy on most tested benchmarks.
By Shengyang Xu, Weijun Zhang, Jun Hu, Pengzhan Jin
Pheno-GS is a new method for computing scalable, geometry-aware optimal transport distances between large patient cohorts of single‑cell data. It uses graph connectivity regularization, an unbalanced OT formulation with KL marginal penalties, and a batched matrix algorithm that dramatically speeds up pairwise distance calculations. The authors validate the approach on synthetic benchmarks and a CyTOF perturbation dataset.
By Alistair Wilkinson, Christopher J. Tape, Smita Krishnaswamy
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
The paper introduces RECAP, a redundancy-aware credit assignment method that improves reasoning efficiency in large language models by assigning credit to each reasoning step based on its downstream role and contribution to the correct answer. RECAP uses a semantic dependency graph to measure structural responsibility and evaluates step efficacy via changes in gold-answer log-likelihood, enabling step-specific updates without requiring a separate reward model or concise trajectories. Experiments on two 7B models across four mathematical reasoning benchmarks show that RECAP enhances the accuracy-efficiency trade-off, boosting pass@1 by 2.0–3.7 percentage points while cutting reasoning tokens by 8–31% compared to GRPO.
By Yuqing Zhou, Hong Wang, Manqing Mao, Zhuoer Wang, Samson Koelle, Jie Yuan, Yanjun Lin, James Feng, Nikki Lijing Kuang, Ziwei Zhu, Wei Niu
arXiv:2609.28283v1 Announce Type: new
Abstract: Several foundation models dedicated to hyperspectral images have recently been made available. These models are trained on large unlabeled datasets and...
By Edgard Dabier, Christophe Kervazo, Pietro Gori, Florence Tupin
arXiv:2609.27654v1 Announce Type: cross
Abstract: Verified income is often unavailable in digital loan applications, forcing lenders to rely on reported income and potentially leading to over-lending...
By Sultan Amed, Tanmay Sen, Sayantan Banerjee
arXiv:2409.13568v3 Announce Type: replace
Abstract: Accurate delineation of agricultural field boundaries is essential for effective crop monitoring and resource management. However, competing method...
By Foivos I. Diakogiannis, Zheng-Shu Zhou, Jeff Wang, Gonzalo Mata, Dave Henry, Roger Lawes, Amy Parker, Peter Caccetta, Suzanne Furby, Rodrigo Ibata, Ondrej Hlinka, Jonathan Richetti, Kathryn Batchelor, Chris Herrmann, Andrew Toovey, John Taylor
The paper argues that large language models (LLMs) organize their internal mathematical reasoning by reusable reasoning approaches rather than by the benchmark topics they are tested on. Using a generation‑replay protocol, the authors extract activation‑importance signatures from eight models across five math sources, cluster these signatures, and find that the resulting groups align more closely with reasoning approaches than with topics. The study shows that changing the requested reasoning approach shifts cluster assignments, while paraphrasing the prompt does not, underscoring the primacy of approach over topic in LLM reasoning.
By Sajad Goudarzi, Samaneh Zamanifard, Moloud Nasiri, Hamed Rahimian
The paper proposes a method to train efficient multi‑task manipulation policies by distilling knowledge from single‑task Conditional Flow Matching (CFM) experts. Instead of training separate models for each task, the authors transfer the experts’ learned velocity fields into a shared policy, combining this distillation signal with the original CFM objective. Experiments on RLBench demonstrate that this approach improves multi‑task performance while keeping the model size fixed, avoiding the need for larger capacity or performance drops seen with naive concatenated training.
By Shreya Deshmukh, Imen Mahdi, Nick Heppert, Abhinav Valada
arXiv:2609.28007v1 Announce Type: cross
Abstract: Most Turkish-capable large language models (LLMs) are evaluated using general-purpose benchmarks rather than long, structurally complex domain docume...
By Imtiaz Ul Hassan, \"Oyk\"u Akbulut, Onur Kaya, Ardhendu Behera, Swagat Kumar, Peter Matthew, Yonghuai Liu
arXiv:2609.27220v1 Announce Type: new
Abstract: Diffusion language models generate text through iterative denoising, exposing intermediate trajectories before final answers are produced. We identify...
By Guoshenghui Zhao, Tan Yu, Weijie Zhao
arXiv:2609.28015v1 Announce Type: cross
Abstract: Data assimilation estimates a dynamical state from partial and noisy observations. Classical ensemble filters are efficient but restrict analysis upd...
By Haoyuan Chen, Alexandre Thi\'ery
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:2609.28099v1 Announce Type: cross
Abstract: Deep vision systems remain vulnerable to corruption, occlusion, and distribution shift despite strong benchmark performance. Existing reliability met...
By Anoushka Harit, Rehan Zuberi, William Prew, Florian Markowetz
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:2609.27490v1 Announce Type: new
Abstract: AI research agents need reliable knowledge of how their experiments change outcomes. We introduce WhatWorkedBench to measure experimental understanding...
By Jingjie Ning, Xueqi Li, Yibo Kong, Dongting Li
arXiv:2609.27606v1 Announce Type: new
Abstract: We introduce State-Grounded Conditioning (SGC), a design principle for user-facing LLM agents that must condition on live user state (game state, sessi...
By Qi Liu, Xiaoyang Yuan, Yubin Ruan, Zhuomeng Zhang, Wenjin Wang, Di Wu, Mingye Xu, Xinyi Mou, Xingxi Yin, Ke Feng, Zixun Sun