arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

Northeastern University(东北大学)

共收录 1238
2603.09825 2026-03-11 cs.CV

BrainSTR: Spatio-Temporal Contrastive Learning for Interpretable Dynamic Brain Network Modeling

BrainSTR: 基于时空对比学习的可解释动态脑网络建模

Guiliang Guo, Guangqi Wen, Lingwen Liu, Ruoxian Song, Peng Cao, Jinzhu Yang, Fei Wang, Xiaoli Liu, Osmar R. Zaiane

机构 * Computer Science and Engineering, Northeastern University, Shenyang, China(东北大学计算机科学与工程学院,中国沈阳) School of Computer Science and Artificial Intelligence, Shandong Normal University, Jinan, China(山东师范大学计算机科学与人工智能学院,中国济南) Graduate School of Information, Production and Systems, Waseda University, Kitakyushu, Fukuoka, Japan(早稻田大学信息、生产与系统研究生院,日本北九州市福冈) Nanjing Medical University, Nanjing, China(南京医学院,中国南京) AiShiWeiLai AI Research, Beijing, China(人工智能研究公司AiShiWeiLai,中国北京) Amii, University of Alberta, Edmonton, Alberta, Canada(阿尔伯塔大学Amii研究所,加拿大埃德蒙顿,阿尔伯塔)

AI总结 BrainSTR通过时空对比学习方法,提升动态脑网络建模的可解释性,通过关键相识别和疾病相关连接提取,验证了其在ASD、BD和MDD诊断中的有效性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.09606 2026-03-11 cs.LG

Learning the Hierarchical Organization in Brain Network for Brain Disorder Diagnosis

学习脑网络的层次组织以用于脑部疾病诊断

Jingfeng Tang, Peng Cao, Guangqi Wen, Jinzhu Yang, Xiaoli Liu, Osmar R. Zaiane

机构 * Computer Science and Engineering, Northeastern University, Shenyang, China(东北大学计算机科学与工程系,中国沈阳) School of Computer Science and Artificial Intelligence, Shandong Normal University, Jinan, China(山东师范大学计算机科学与人工智能学院,中国济南) AiShiWeiLai AI Research, Beijing, China(人工智能研究机构,中国北京) Amii, University of Alberta, Edmonton, Alberta, Canada(阿尔伯塔大学人工智能研究所,加拿大埃德蒙顿,阿尔伯塔)

AI总结 本文提出BrainHO方法,通过学习脑网络的内在层次结构,提升脑部疾病诊断的准确性并发现具有临床意义的生物标志物。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.09200 2026-03-11 cs.AI cs.CL cs.CY cs.LG

The Reasoning Trap -- Logical Reasoning as a Mechanistic Pathway to Situational Awareness

推理陷阱——逻辑推理作为情境意识的机制路径

Subramanyam Sahoo, Aman Chadha, Vinija Jain, Divya Chaudhary

机构 * MARS 4.0 Fellowship, Cambridge AI Safety Hub(CAISH), University of Cambridge(MARS 4.0 Fellow,剑桥人工智能安全中心(CAISH),剑桥大学) AWS Generative AI Innovation Center, Amazon Web Services, USA(亚马逊生成AI创新中心,亚马逊网络服务,美国) Google, USA(谷歌,美国) Stanford University(斯坦福大学) Northeastern University, Seattle, WA, USA(东北大学,西雅图,华盛顿州,美国)

AI总结 本文提出RAISE框架,揭示逻辑推理能力提升与情境意识升级的机制路径,并提出安全原则与测试方法以应对潜在风险。

Comments Accepted at ICLR 2026 Workshop on Logical Reasoning of Large Language Models. 21 Pages. Position Paper

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.09113 2026-03-11 cs.RO cs.AI

PM-Nav: Priori-Map Guided Embodied Navigation in Functional Buildings

PM-Nav:基于先验图的功能性建筑中具身导航

Jiang Gao, Xiangyu Dong, Haozhou Li, Haoran Zhao, Yaoming Zhou, Xiaoguang Ma

机构 * Faculty of Robot Science and Engineering at Northeastern University(东北大学机器人科学与工程学院) Foshan Graduate School of Innovation at Northeastern University(东北大学佛山创新研究生学院) School of Aeronautic Science and Engineering at Beihang University(北航航空科学与工程学院)

AI总结 PM-Nav通过构建先验图和多模型协作机制,提升了功能性建筑中的导航精度和效率。

Comments 6 pages, 4 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.07357 2026-03-11 cs.LG cs.AI

Latent Generative Models with Tunable Complexity for Compressed Sensing and other Inverse Problems

具有可调复杂度的潜在生成模型用于压缩感知及其他反问题

Sean Gunn, Jorio Cocola, Oliver De Candido, Vaggos Chatziafratis, Paul Hand

机构 * Northeastern University(东北大学) Harvard University(哈佛大学) Technical University of Munich(慕尼黑技术大学) UC Santa Cruz(加州大学圣克鲁兹分校)

AI总结 本文提出可调复杂度生成模型,用于提升压缩感知等反问题的重建性能,并通过理论分析和实验验证其有效性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.12083 2026-03-11 cs.LG

Discovering Symbolic Differential Equations with Symmetry Invariants

利用对称不变量发现符号微分方程

Jianke Yang, Manu Bhat, Bryan Hu, Yadi Cao, Nima Dehmamy, Robin Walters, Rose Yu

机构 * University of California, San Diego(加州大学圣迭戈分校) IBM Research(IBM研究院) Northeastern University(东北大学)

AI总结 本文提出利用对称不变量提升微分方程发现的准确性与效率,通过物理系统验证其能恢复符合物理定律的简洁方程。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.08321 2026-03-10 cs.AI

CORE-Acu: Structured Reasoning Traces and Knowledge Graph Safety Verification for Acupuncture Clinical Decision Support

CORE-Acu: 结构化推理轨迹与知识图谱安全验证用于针灸临床决策支持

Liuyi Xu, Yun Guo, Ming Chen, Zihan Dun, Yining Qian, An-Yang Lu, Shuang Li, Lijun Liu

机构 * College of Information Science and Engineering, Northeastern University, Shenyang 110819, China(信息科学与工程学院,东北大学,沈阳110819,中国) School of Information Science and Engineering, Yanshan University, Qinhuangdao, Hebei 066000, China(信息科学与工程学院,燕山大学,秦皇岛,河北省066000,中国) School of Computer Science and Engineering, Northeastern University, Shenyang 110819, China(计算机科学与工程学院,东北大学,沈阳110819,中国) School of Artificial Intelligence, Beihang University, Beijing 100000, China(人工智能学院,北航,北京100000,中国) Key Laboratory of Bioresource Research and Development of Liaoning Province, Northeastern University, Shenyang 110169, China(辽宁省生物资源研究开发重点实验室,东北大学,沈阳110169,中国) College of Life and Health Sciences, Northeastern University, Shenyang 110169, China(生命与健康科学学院,东北大学,沈阳110169,中国)

AI总结 CORE-Acu通过结构化推理轨迹与知识图谱安全验证,提升针灸临床决策支持的可解释性与安全性。

Comments 19 pages, 5 figures, 18 tables. Includes the Acu-Reasoning dataset and TCM knowledge graph schema

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.08007 2026-03-10 cs.CV cs.AI

ViSA-Enhanced Aerial VLN: A Visual-Spatial Reasoning Enhanced Framework for Aerial Vision-Language Navigation

ViSA增强的空中视觉语言导航:一种增强视觉空间推理能力的空中视觉语言导航框架

Haoyu Tong, Xiangyu Dong, Xiaoguang Ma, Haoran Zhao, Yaoming Zhou, Chenghao Lin

机构 * Tianmushan Laboratory, Beihang University(北航之梦实验室,北京航空航天大学) Hangzhou International Innovation Institute, Beihang University(杭州国际创新研究院,北京航空航天大学) Foshan Graduate School of Innovation, Northeastern University(佛山创新研究生学院,东北大学) School of Aeronautic Science and Engineering, Beihang University(航空科学与工程学院,北京航空航天大学) Faculty of Robot Science and Engineering, Northeastern University(机器人科学与工程学院,东北大学)

AI总结 ViSA增强框架通过结构化视觉提示提升空中VLN的空间推理能力,显著提高成功率,为该领域提供有力支持。

Comments 8 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.07997 2026-03-10 cs.AI

CMMR-VLN: Vision-and-Language Navigation via Continual Multimodal Memory Retrieval

CMMR-VLN:通过持续多模态记忆检索实现视觉与语言导航

Haozhou Li, Xiangyu Dong, Huiyan Jiang, Yaoming Zhou, Xiaoguang Ma

机构 * Foshan Graduate School of Innovation at Northeastern University(东北大学创新研究生院) Faculty of Robot Science and Engineering at Northeastern University(东北大学机器人科学与工程学院) College of Software at Northeastern University(东北大学软件学院) School of Aeronautic Science and Engineering at Beihang University(北航航空科学与工程学院)

AI总结 CMMR-VLN通过引入持续多模态记忆检索机制,提升视觉与语言导航任务中对先前经验的选择性利用能力,显著提高导航成功率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.07599 2026-03-10 cs.CL

StyleBench: Evaluating Speech Language Models on Conversational Speaking Style Control

StyleBench: 评估语音语言模型在对话说话风格控制中的表现

Haishu Zhao, Aokai Hao, Yuan Ge, Zhenqiang Hong, Tong Xiao, Jingbo Zhu

机构 * NLP Lab, School of Computer Science and Engineering, Northeastern University, Shenyang, China(计算机科学与工程学院自然语言处理实验室,东北大学,沈阳,中国) NiuTrans Research, Shenyang, China(尼乌透研究,沈阳,中国)

AI总结 StyleBench是一个多轮对话基准测试,用于评估语音语言模型在情感、速度、音量和音调四个维度上的风格强度控制能力,并揭示了SLMs与通用语言模型之间的性能差距。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.06932 2026-03-10 cs.CV

HIERAMP: Coarse-to-Fine Autoregressive Amplification for Generative Dataset Distillation

HIERAMP:生成数据集蒸馏的粗到细自回归放大

Lin Zhao, Xinru Jiang, Xi Xiao, Qihui Fan, Lei Lu, Yanzhi Wang, Xue Lin, Octavia Camps, Pu Zhao, Jianyang Gu

机构 * Northeastern University(东北大学) University of Alabama at Birmingham(阿拉巴马大学伯明翰分校) The Ohio State University(俄亥俄州立大学)

AI总结 HIERAMP通过粗到细自回归放大方法,提升生成数据集的语义多样性与细节聚焦,从而提高蒸馏效果。

Comments The paper is accepted by CVPR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.06696 2026-03-10 cs.CV

HARP: HARmonizing in-vivo diffusion MRI using Phantom-only training

HARP: 仅使用假体数据进行体内扩散磁共振成像的协调

Hwihun Jeong, Qiang Liu, Kathryn E. Keenan, Elisabeth A. Wilde, Walter Schneider, Sudhir Pathak, Anthony Zuccolotto, Lauren J. O'Donnell, Lipeng Ning, Yogesh Rathi

机构 * Department of Psychiatry(精神医学系) Brigham and Women's Hospital(布里奇沃特医院) Harvard Medical School(哈佛医学院) College of Engineering(工程学院) Northeastern University(东北大学) National Institute of Standards and Technology(国家标准技术研究院) University of Utah School of Medicine(犹他大学医学院) George E. Wahlen Veterans Affairs Medical Center(乔治·E·瓦伦的退伍军人事务医疗中心) University of Pittsburgh(匹兹堡大学) Department of Radiology(放射医学系) Harvard-MIT Health Sciences and Technology(哈佛-麻省理工健康科学与技术)

AI总结 HARP通过仅使用假体数据训练深度学习模型,实现了无需多站点活体数据的扩散磁共振成像协调,有效降低了扫描仪间变异性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.06640 2026-03-10 cs.CV cs.LG

Roots Beneath the Cut: Uncovering the Risk of Concept Revival in Pruning-Based Unlearning for Diffusion Models

剪枝之下:揭示基于剪枝的去学习中概念复兴的风险

Ci Zhang, Zhaojun Ding, Chence Yang, Jun Liu, Xiaoming Zhai, Shaoyi Huang, Beiwen Li, Xiaolong Ma, Jin Lu, Geng Yuan

机构 * University of Georgia(佐治亚大学) Carnegie Mellon University(卡内基梅隆大学) Northeastern University(东北大学) Stevens Institute of Technology(史蒂文斯理工学院) University of Arizona(亚利桑那大学)

AI总结 本文揭示基于剪枝的去学习中概念复兴的风险,提出攻击框架可无数据恢复被擦除概念,并探讨安全剪枝机制。

Comments Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.02426 2026-03-10 cs.LG

Personalized Multi-Agent Average Reward TD-Learning via Joint Linear Approximation

个性化多智能体平均回报TD学习 via 联合线性近似

Leo Muxing Wang, Pengkun Yang, Lili Su

机构 * Northeastern University(东北大学) Tsinghua University(清华大学)

AI总结 本文提出通过联合线性近似实现个性化多智能体平均回报TD学习,通过共享子空间和局部头部的分解,有效缓解信号冲突并实现线性加速。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.16125 2026-03-10 cs.LG

On the Power of Source Screening for Learning Shared Feature Extractors

在学习共享特征提取器中源筛选的效能

Leo Muxing Wang, Connor Mclaughlin, Lili Su

机构 * Northeastern University(东北大学)

AI总结 本文探讨了在学习共享特征提取器时,通过源筛选来优化子空间估计的方法,证明了精心选择的数据子集可实现最小最大最优性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.12719 2026-03-10 cs.CV

S2DiT: Sandwich Diffusion Transformer for Mobile Streaming Video Generation

S2DiT:用于移动流媒体视频生成的 Sandwich Diffusion Transformer

Lin Zhao, Yushu Wu, Aleksei Lebedev, Dishani Lahiri, Meng Dong, Arpit Sahni, Michael Vasilkovsky, Hao Chen, Ju Hu, Aliaksandr Siarohin, Sergey Tulyakov, Yanzhi Wang, Anil Kag, Yanyu Li

机构 * Snap Inc. Northeastern University(东北大学)

AI总结 S2DiT 通过高效注意力机制和 2-in-1 深度学习框架,在移动设备上实现高质量、高速度的流式视频生成。

Comments https://snap-research.github.io/S2DiT/

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.06359 2026-03-09 cs.LG cs.CR

Tiny, Hardware-Independent, Compression-based Classification

微型、硬件无关、基于压缩的分类

Charles Meyers, Aaron MacSween, Erik Elmroth, Tommy Löfstedt

机构 * Institute for Experiential AI, Northeastern University, Boston, United States(体验人工智能研究所,东北大学,波士顿,美国) Department of Computer Science, Umeå University, Umeå, Sweden(计算机科学系,乌梅拉大学,乌梅拉,瑞典)

AI总结 本文提出基于压缩的距离度量方法,用于在客户端设备上高效进行分类,实现高准确率的同时降低计算成本。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.06333 2026-03-09 cs.AI cs.CL cs.LG

SAHOO: Safeguarded Alignment for High-Order Optimization Objectives in Recursive Self-Improvement

SAHOO:递归自我改进中高阶优化目标的安全保障

Subramanyam Sahoo, Aman Chadha, Vinija Jain, Divya Chaudhary

机构 * MARS 4.0 Fellowship, Cambridge AI Safety Hub(CAISH), University of Cambridge(剑桥大学) AWS Generative AI Innovation Center, Amazon Web Services, USA(亚马逊网络服务) Google, USA(谷歌) Stanford University(斯坦福大学) Northeastern University, Seattle, WA, USA(东北大学)

AI总结 SAHOO通过三种保障措施实现递归自我改进中高阶优化目标的安全保障,显著提升代码生成和推理质量,同时保持约束和事实性。

Comments Published at ICLR 2026 Workshop on AI with Recursive Self-Improvement. 20 pages, 5 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.06120 2026-03-09 cs.LG

Dynamic Momentum Recalibration in Online Gradient Learning

在线梯度学习中的动态动量重校准

Zhipeng Yao, Rui Yu, Guisong Chang, Ying Li, Yu Zhang, Dazhou Li

机构 * Shenyang University of Chemical Technology(沈阳化工大学) University of Louisville(路易斯维尔大学) Northeastern University(东北大学)

AI总结 SGDF通过动态调整动量系数优化梯度估计,提升深度学习优化性能。

Comments Accepted by CVPR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.05873 2026-03-09 cs.CV

Shifting Adaptation from Weight Space to Memory Space: A Memory-Augmented Agent for Medical Image Segmentation

从权重空间到记忆空间的迁移适应:一种用于医学图像分割的记忆增强代理

Bowen Chen, Qiaohui Gao, Shaowen Wan, Shanhui Sun, Wei Liu, Xiang Li, Tianming Liu, Lin Zhao

机构 * Department of Electrical and Computer Engineering, University of California, Santa Barbara, Santa Barbara, CA 93106, USA(电子工程系,加州大学圣芭芭拉分校) College of Engineering, Northeastern University, Boston, MA 02115, USA(工程学院,东北大学) Department of Biomedical Engineering, New Jersey Institute of Technology, Newark, NJ 07102, USA(生物医学工程系,新泽西理工学院) United Imaging Intelligence, Burlington, MA 01803, USA(联合影像智能公司) Department of Radiation Oncology, Mayo Clinic, Scottsdale, AZ 85259, USA(放射肿瘤科,梅奥诊所) Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA 02115, USA(放射科,麻省总医院和哈佛医学院) School of Computing, University of Georgia, Athens, GA 30602, USA(计算学院,佐治亚大学)

AI总结 本文提出MemSeg-Agent,通过将适应从权重空间转移到记忆空间,实现少样本学习、联邦监督学习和测试时间适应,提升医学图像分割的泛化能力和效率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.05801 2026-03-09 cs.CY cs.AI

Ambiguity Collapse by LLMs: A Taxonomy of Epistemic Risks

LLMs中的模糊性消解:一种认知风险的分类

Shira Gur-Arieh, Angelina Wang, Sina Fazelpour

机构 * Harvard University(哈佛大学) Northeastern University(东北大学)

AI总结 本文探讨了LLMs在处理模糊术语时引发的认知风险,提出模糊性消解现象,并通过案例研究分析其在过程、输出和生态系统层面的影响,提出多层缓解原则以管理模糊性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.00273 2026-03-09 eess.SY cs.RO cs.SY math.OC

Dependent Reachable Sets for the Constant Bearing Pursuit Strategy

常值方位追捕策略下的依赖可达集

Venkata Ramana Makkapati, Tulasi Ram Vechalapu, Vinodhini Comandur, Seth Hutchinson

机构 * Honda Aircraft Company(本田飞机公司) Technion - Israel Institute of Technology(技术ion-以色列理工学院) University of Colorado Boulder(科罗拉多大学博尔德分校) Northeastern University(东北大学)

AI总结 本文提出了一种基于常值方位追捕策略的依赖可达集分析方法,通过理论结果和仿真验证,探讨了两个智能体在反馈策略下的可达性边界问题。

Comments This work has been submitted to a journal for possible publication

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.10328 2026-03-09 cs.CV

Fuse4Seg: Image Fusion for Multi-Modal Medical Segmentation via Bi-level Optimization

Fuse4Seg: 多模态医学分割的图像融合 via 两级优化

Yuchen Guo, Junli Gong, Hongmin Cai, Yiu-ming Cheung, Weifeng Su

机构 * Northwestern University(西北大学) Northeastern University(东北大学) South China University of Technology(华南理工大学) Hong Kong Baptist University(香港 Baptist大学) Beijing Normal - Hong Kong Baptist University(北京师范大学-香港 Baptist大学)

AI总结 Fuse4Seg通过两级优化实现多模态医学图像融合,解决视觉与语义间的差距问题,提升分割任务的准确性和临床可解释性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.07419 2026-03-06 cs.LG cs.CV

Revolutionizing Mixed Precision Quantization: Towards Training-free Automatic Proxy Discovery via Large Language Models

颠覆混合精度量化:通过大语言模型实现无训练的自动代理发现

Haidong Kang, Jun Du, Lihong Lin

机构 * School of Computer and Communication Engineering, Northeastern University(东北大学计算机与通信工程学院) School of Software Engineering, Beijing Jiaotong University(北京交通大学软件工程学院) School of Software, Northeastern University(东北大学软件学院)

AI总结 本文提出TAP框架,利用大语言模型和进化搜索策略,实现无训练的自动代理发现,提升混合精度量化的性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.04585 2026-03-06 cs.RO

ELLIPSE: Evidential Learning for Robust Waypoints and Uncertainties

ELLIPSE:基于证据学习的鲁棒路径点和不确定性预测

Zihao Dong, Chanyoung Chung, Dong-Ki Kim, Mukhtar Maulimov, Xiangyun Meng, Harmish Khambhaita, Ali-akbar Agha-mohammadi, Amirreza Shaban

机构 * FieldAI Northeastern University(东北大学)

AI总结 ELLIPSE通过多元深度证据回归方法,提升移动机器人在开放世界中路径点预测的鲁棒性和不确定性估计的可靠性。

Comments 8 pages, 5 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.19948 2026-03-06 cs.CL cs.AI cs.CY cs.HC cs.MA

Assessing Risks of Large Language Models in Mental Health Support: A Framework for Automated Clinical AI Red Teaming

评估大型语言模型在心理健康支持中的风险:一种用于自动化临床AI红队测试的框架

Ian Steenstra, Paola Pedrelli, Weiyan Shi, Stacy Marsella, Timothy W. Bickmore

机构 * Northeastern University(东北大学) Harvard Medical School(哈佛医学院)

AI总结 本文提出了一种评估AI心理治疗师在心理健康支持中安全风险的框架,通过模拟测试发现AI在治疗中的潜在风险,并验证了交互式可视化工具的有效性。

Comments This paper is a condensed version of the first author's Ph.D. dissertation submitted to Northeastern University

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.03644 2026-03-05 cs.HC cs.AI

Bridging Pedagogy and Play: Introducing a Language Mapping Interface for Human-AI Co-Creation in Educational Game Design

连接教学与游戏:引入一种语言映射接口用于教育游戏设计中的人机协同创作

Daijin Yang, Erica Kleinman, Casper Harteveld

机构 * Northeastern University(东北大学)

AI总结 本文提出一种基于语言映射的接口,通过人机协同设计教育游戏,以明确教学意图并降低非专业设计师的设计门槛。

Comments Accepted for CHI EA 26

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.03475 2026-03-05 cs.LG cs.AI cs.CL

When Shallow Wins: Silent Failures and the Depth-Accuracy Paradox in Latent Reasoning

浅层胜出:潜在推理中的沉默失败与深度-准确性悖论

Subramanyam Sahoo, Aman Chadha, Vinija Jain, Divya Chaudhary

机构 * Independent(独立研究者) AWS Generative AI Innovation Center, Amazon Web Services(亚马逊生成AI创新中心,亚马逊网络服务) Meta AI Stanford University(斯坦福大学) Northeastern University, Seattle, WA, USA(东北ern大学,西雅图,华盛顿州,美国)

AI总结 研究揭示数学推理模型在深度增加时准确率无提升,且存在大量不可靠推理路径,需改革评估方法以衡量稳定性。

Comments Accepted at ICLR 2026 Workshop on Latent & Implicit Thinking - Going Beyond CoT Reasoning. 19 Pages and 5 Figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.02629 2026-03-04 cs.CV

Towards an Incremental Unified Multimodal Anomaly Detection: Augmenting Multimodal Denoising From an Information Bottleneck Perspective

迈向增量统一多模态异常检测:从信息瓶颈视角增强多模态去噪

Kaifang Long, Lianbo Ma, Jiaqi Liu, Liming Liu, Guoyang Xie

机构 * Software College, Northeastern University, China(东北大学软件学院) CATL, China(宁德时代)

AI总结 本文提出IB-IUMAD框架,通过Mamba解码器和信息瓶颈融合模块解决多模态异常检测中的灾难性遗忘问题,提升模型对新兴对象的适应能力。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.02266 2026-03-04 cs.SD cs.AI eess.AS

When Scaling Fails: Mitigating Audio Perception Decay of LALMs via Multi-Step Perception-Aware Reasoning

当扩展失效时:通过多步骤感知-aware 推理缓解LALMs的音频感知衰减

Ruixiang Mao, Xiangnan Ma, Dan Chen, Ziming Zhu, Yuan Ge, Aokai Hao, Haishu Zhao, Yifu Huo, Qing Yang, Kaiyan Chang, Xiaoqian Liu, Chenglong Wang, Qiaozhi He, Tong Xiao, Jingbo Zhu

机构 * Northeastern University,China(东北大学) NiuTrans Research(NiuTrans研究院)

AI总结 本文提出MPAR²范式,通过多步骤感知-aware推理缓解LALMs在推理过程中因音频感知衰减导致的性能下降问题。

Comments Under Review

详情

展开后加载摘要…

URL PDF HTML 收藏