The paper demonstrates that row-wise normalization can achieve higher population accuracy than full-batch Adam, a proxy for random-reshuffling Adam, and exact-SVD Muon in high-dimensional multiclass classification. Under an isotropic Gaussian-cloud data model, this advantage stems from row normalization’s class-wise Euclidean geometry preserving decision-boundary directions, whereas Adam’s coordinate-wise geometry and Muon’s spectral geometry introduce distortions. The advantage also persists in more general settings, including class means with independently oriented covariances, power-law spectra with class-mean exponent below one, and even under heavily anisotropic test noise, though it can reverse when covariances are diagonal and close, unless a random rotation aligns them with Adam’s coordinate axes.
By Jihwan Kim, Dogyoon Song, Chulhee Yun
MetaEncoder is a bi‑encoder model that transforms a pre‑trained Muse‑Glimmer 30B decoder into an instruction‑following decision‑making encoder for multimodal systems. It represents both user requests and candidate options in natural language, leveraging image and video inputs, and uses unidirectional contrastive learning to align requests with candidates across both small closed‑set and large open‑set spaces. Extensive tests on 11 benchmark suites and 190 tasks show MetaEncoder surpasses state‑of‑the‑art multimodal encoders in many areas, while still facing challenges on reasoning‑intensive tasks.
By Jianpeng Cheng, Guangyu Sun, Aashu Singh, Benyu Zhang, Haixing Dai, Hossein Mansour, Jiangfan Zhang, Shlok Kumar Mishra, Wei Sun, Xuanming Cui, Yanli Liu, Qi Guo, Max Xiangjun Fan, Jun Xiao
Fair-GPTQ is a quantization method for large language models that incorporates explicit group‑fairness constraints into the quantization objective. By guiding the rounding operation, it reduces bias in generated text, particularly for occupational stereotypes and discriminatory language across gender, race, and religion. The approach maintains at least 90 % of baseline accuracy on zero‑shot benchmarks while preserving the memory and speed benefits of 4‑bit quantization.
By Irina Proskurina, Guillaume Metzler, Julien Velcin
The paper introduces CAMEO, a framework for generating ultrasound reports from multiple images that emphasizes clinical awareness and evidence grounding. It consists of three stages: learning visual-language primitives, cross-view evidence grounding using distilled image-report pairs, and clinically aware preference alignment with error-oriented pairs. Experiments on the USReport-Distilled benchmark show significant improvements over prior models in BLEU, ROUGE, METEOR, and ClinicalScore metrics.
By Yuchen Yang, Xin Wang, Lufan Wang, Yinghong Pan, Yujuan Feng, Yuqing Yang
EchoDiST is an unsupervised framework for estimating myocardial motion in echocardiography, combining self‑distillation joint learning of anatomical segmentation and motion estimation with a diffusion‑conditioned network. The method uses limited anatomical annotations and stochastic perturbations during training, yet requires only a single deterministic forward pass at inference. Evaluated on three datasets, EchoDiST consistently outperforms seven other learning‑based approaches in anatomical alignment, strain assessment, and functional metrics, with statistically significant improvements across cross‑view and cross‑dataset tests.
By Feiyue Qi, Xingyue Wei, Jianwen Luo
The paper introduces Motion‑Aware Deepfake (MAD) videos, a new class of deepfakes generated by pose‑guided diffusion models that can animate entire human figures. To study this threat, the authors build the first MAD‑specific benchmark with 1.5 million frames from 1,363 real and 30,122 synthetic videos, and analyze the subtle high‑frequency artifacts and spectral fingerprints that arise from limited input frames. Leveraging these insights, they propose MoDA, a defense framework that combines spatial semantics with steganalysis‑rich frequency features, achieving high detection and attribution accuracy across in‑distribution, cross‑dataset, and zero‑shot scenarios, and demonstrating robustness against adaptive attacks.
By Fazhong Liu, Yan Meng, Tian Dong, Guoxing Chen, Haojin Zhu
The paper introduces the "ontology tower," a narrow-and-deep ontology designed for a single industrial equipment system. By enriching knowledge through derived quantities and operational lessons, the ontology improves large language model agents’ performance on plant tasks, raising error avoidance by ~20 percentage points and matching the largest models’ scores. In live safety tests, agents guided the system’s controlled variable into target ranges in 12 of 14 runs.
By Younghwan Joo, Sung-il Kim
AuraLuxMuse is a system that automates aesthetic stage lighting design by integrating expert knowledge, representation learning, and preference-adaptive modeling. It encodes music and professional cue sequences into a shared retrieval space, estimates cue-event density, and retargets fixture commands to the stage, providing editable cues for designers. The system features Lighting‑Aligned Music Pretraining (LAMP) for audio‑lighting alignment and Preference‑Adaptive Mixture of Experts (PAMoE) for designer‑intent‑driven cue adaptation, and is evaluated using the new Musilux dataset and both virtual and professional labs.
By Junyu Deng, Jiale Cao, Mengtian Li, Zhongxia Ji, Ruhua Chen, Yiyi He, Guangnan Ye, Zuo Hu
The paper introduces Spatial Alignment via Geometric Evolution (SAGE), a self‑evolving framework designed to strengthen robust spatial reasoning in Vision‑Language Models (VLMs). SAGE leverages geometric and linguistic duality operations, incorporating duality consistency into training to ensure coherent answers across original and transformed inputs. The method dynamically updates its operation pool, focusing on challenging dualities while retiring mastered ones, and is model‑agnostic, data‑efficient, and applicable as a lightweight adaptation stage to existing VLMs, yielding consistent improvements on video and spatial reasoning benchmarks.
By Junming Liu, Yuqi Li, Yifei Sun, Maonan Wang, Yiming Cheng, Rui Qian, Piotr Koniusz, Yirong Chen, Ding Wang
The paper introduces an explainable, header‑centric framework for semantic table interpretation and data quality assessment that operates solely on column headers. It maps headers to 39 interpretable types using curated lexical resources, applies validation rules to detect data quality issues, and aggregates these into a lightweight quality metric called HeadersIQ. The framework was evaluated on diverse benchmarks, demonstrating broad coverage of noisy real‑world metadata and providing a workflow for metadata‑driven semantic annotation, quality monitoring, and benchmark diagnosis.
By Marcelo Valentim Silva, Hannes Herrmann, Valerie Maxville
The paper investigates the sample‑efficiency of Kolmogorov‑Arnold Networks (KANs) in reinforcement learning. Using experiments on the Feynman dataset and Gymnasium benchmarks, the authors find that KANs achieve comparable performance to standard Multi‑Layer Perceptrons while requiring 40% fewer samples, with up to 50% relative performance gains during training. These improvements hold even when reward noise varies, underscoring KANs’ potential for more sample‑efficient RL.
By Kevin Riehl, Shaimaa K. El-Baklish, Fan Wu, Anastasios Kouvelas
arXiv:2610. 11074v1 Announce Type: new Abstract: We establish near-optimal regret bounds for budget-constrained online learning against arbitrary classes of budget-pacing experts in the adversarial setting.
By Mark Braverman, Jingyi Liu, Jieming Mao, Jon Schneider, Eric Xue
The paper presents a scalable method for meta‑learning interpretable decision trees by generating synthetic pre‑training data. It samples near‑optimal trees to create large, realistic datasets and uses the MetaTree transformer architecture to match the performance of real‑world pre‑training or costly optimal tree training. This approach cuts computational costs, offers flexible data generation, and supports efficient, scalable meta‑learning of decision trees.
By Kyaw Hpone Myint, Zhe Wu, Alexandre G. R. Day, Giri Iyengar
arXiv:2512. 13892v3 Announce Type: replace-cross Abstract: Reliable estimation of feature contributions in machine learning models is essential for transparency, algorithmic fairness, and regulatory compliance.
By Albert Dorador
The paper investigates how the imperative mood in system prompt instructions influences instruction topology across languages. Experiments on four languages and four models show that imperative instructions can invert cooperative and competitive interaction patterns, and that rewriting these instructions to declarative form reduces cross‑linguistic variance by 81%. The study suggests that language‑dependent social register shapes how large language models interpret instructions, implying that imperative‑mood directives may lead to language‑specific alignment during training and inference.
By Tony Mason
The paper evaluates EEG foundation models (EEG‑FMs) beyond clean accuracy, testing six models and a supervised baseline across ten datasets. It finds that no single model excels in all robustness tests, that attribution methods reveal task‑appropriate brain region relevance, and that poor head‑only performance is largely due to pooling strategies rather than representation quality. The study also shows that fine‑tuning repurposes late blocks while early blocks already encode task information.
By Urban \v{S}irca, Maryam Alimardani, Stefanos Zafeiriou, Konstantinos Barmpas
The paper introduces Adversarial Heuristic Learning (AHL), a framework that uses AI agents to refine game policies without changing model weights. It presents AAArena, a benchmark of 12 adversarial games and 1,920 human programs, where agents analyze replays, select opponents, and revise policies to maximize ranking within limited budgets. Experiments show that certain configurations achieve gold medals, while performance drops in games with complex rules, highlighting challenges in game understanding and long‑horizon policy development.
By Kaisen Yang, Qingle Liu, Kejin Wang, Yicheng Zhao, Jieming Li, Shenghan Zheng, Ruize Yang, Bojun Yang, Heng Gong, Xiang Gao, Lanyue Zhang, Kaiyu Zhong, Zhuo Liu, Shaoxuan Li, Chengxi Li, Yong Yan, Weixuan Zhang, Tianwei Luo, Situ Wang, Youjie Zheng, Sihan Zhao, Shengyuan Wang, Huan-ang Gao, Jiazheng Xu, Xiaohui Xie, Wentao Han, Hongning Wang
The article discusses how AI foundation models trained on weather and climate data are increasingly fine‑tuned for a wide range of Earth science tasks beyond traditional weather forecasting. It highlights that current evaluations rely mainly on benchmark skill metrics, which assess forecast accuracy but not the models’ representation of underlying physical processes, a gap that becomes critical under changing climate conditions. The authors propose five priorities for physical evaluation—covering training data, fine‑tuning, behavioral testing, mechanistic interpretability, and output validation—and recommend three actions for the next decade: open AI‑ready evaluation datasets, a shared physics‑based reporting standard, and a dedicated research program on model safety.
By Makoto Kelp, Amirhossein Arzani, Patricia Castellanos, Paul Griffiths, Ivan Higuera-Mendieta, Manuel Perez-Carrasco, Viral Shah, Patrick Obin Sturm, James Weber
The paper surveys how large language models (LLMs) are being used in hardware verification, covering tasks such as assertion generation, testbench creation, bug localization, and formal reasoning. It categorizes the literature by methodology, verification goal, tool interaction, benchmarks, and evaluation metrics, and distinguishes between inference-time techniques (prompting, retrieval, structured reasoning, agentic workflows) and training-time adaptation. The authors highlight that LLMs excel as semantic reasoning, search, and orchestration components within verification workflows, yet emphasize the need for semantic alignment, scalable integration, generalization, and rigorous evaluation to ensure true verification correctness.
By Hao Zheng, Jaime Rafael Imperial, Bardia Nadimi, Xiangfei Kong
ScaleCast is a regional forecasting framework that aligns pretrained global weather models with high‑resolution regional data. It uses a Global‑Regional Conversion module to map joint representations onto regional locations and a Global‑Regional Alignment and Dynamics block to merge global guidance with local neighborhood interactions. Experiments on ERA5 and CERRA data show improved forecasts across surface and upper‑air variables, and the model adapts to different global drivers and a finer 3 km HRRR domain, with case studies indicating better cyclone positioning and temperature/humidity agreement with observations.
By Guowen Li, Yang Liu, Yujie Wang, Qiuyan Sun, Haoyuan Liang, Juepeng Zheng, Hong Cheng, Haohuan Fu