arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

Georgia Institute of Technology(佐治亚理工学院)

共收录 1666
2601.10085 2026-05-28 cs.CL

CALM-IT: Generating Realistic Long-Form Motivational Interviewing Dialogues with Dual-Actor Conversational Dynamics Tracking

CALM-IT: 通过双角色对话动态追踪生成逼真的长形式动机访谈对话

Viet Cuong Nguyen, Nhi Yen Nguyen, Kristin A. Candan, Mary Conlon, Vanessa Rumie, Kristen Risola, Michael L. Birnbaum, Munmun De Choudhury

机构 * Georgia Institute of Technology(佐治亚理工学院) Northwell Health(北well健康) Columbia University(哥伦比亚大学)

AI总结 提出CALM-IT框架,通过显式建模客户与咨询师状态的演变来生成和评估长形式动机访谈对话,在8,232个合成对话语料上优于基线方法,尤其在MITI 4.2全局评分和客户接受率上表现最佳。

Comments 53 pages, in submission to EMNLP

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.05291 2026-05-28 cs.CL

Camellia: Benchmarking Cultural Biases in LLMs for Asian Languages

Camellia: 亚洲语言中LLMs文化偏见的基准测试

Tarek Naous, Anagha Savit, Carlos Rafael Catalan, Geyang Guo, Jaehyeok Lee, Kyungdon Lee, Lheane Marie Dizon, Mengyu Ye, Neel Kothari, Sahajpreet Singh, Sarah Masud, Tanish Patwa, Trung Thanh Tran, Zohaib Khan, Alan Ritter, Tanmoy Chakraborty, Yuki Arase, Keisuke Sakaguchi, JinYeong Bak, Wei Xu

机构 * Georgia Institute of Technology(佐治亚理工学院) Samsung R&D Institute Philippines(三星菲律宾研发院) Sungkyunkwan University(成均馆大学) Tohoku University(东北大学) National University of Singapore(新加坡国立大学) University of Copenhagen(哥本哈根大学) University of Michigan(密歇根大学) Indian Institute of Technology Delhi(印度理工学院德里) Institute of Science Tokyo(东京科学研究院)

AI总结 提出Camellia基准,通过三个任务评估九种亚洲语言中多语言大模型对亚洲与西方文化实体的偏见,发现模型存在文化适应困难、情感关联差异及实体提取性能差距。

详情

展开后加载摘要…

URL PDF HTML 收藏
2311.02304 2026-05-28 cs.RO

Imitating and Finetuning Model Predictive Control for Robust and Symmetric Quadrupedal Locomotion

模仿与微调模型预测控制实现鲁棒且对称的四足运动

Donghoon Youm, Hyunyoung Jung, Hyeongjun Kim, Jemin Hwangbo, Hae-Won Park, Sehoon Ha

机构 * Korea Advanced Institute of Science and Technology(韩国科学技术院) Georgia Institute of Technology(佐治亚理工学院)

AI总结 提出模仿与微调模型预测控制(IFM)框架,结合模型预测控制与模仿学习及强化学习,提升四足机器人在复杂地形上的运动性能、对称性和能效。

Journal ref IEEE Robotics and Automation Letters ( Volume: 8, Issue: 11, November 2023

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.27245 2026-05-27 cs.LG

Symbolic Regression via Latent Iterative Refinement

通过潜在迭代细化的符号回归

Xieting Chu, Sriram Vishwanath, Vijay Ganesh

机构 * Georgia Institute of Technology(佐治亚理工学院)

AI总结 提出潜在方程嵌入(LEE)框架,通过迭代推断在功能基础化的潜在空间中缩小符号回归的推断差距,生成更简单且准确的表达式。

Comments Preprint. 21 pages, 11 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.26582 2026-05-27 cs.LG cs.AI

On the Error-Correcting Effects of Stochasticity in Discrete Diffusion

离散扩散中随机性的纠错效应

William Yuan, Sungwon Jeong, Amirali Aghazadeh

机构 * Georgia Institute of Technology(佐治亚理工学院)

AI总结 本文系统研究离散扩散模型中马尔可夫转移随机性程度对采样效率与质量的权衡,提出离散搅动与重启采样(DCRS)算法,通过交替正向和反向扩散过程注入受控随机性,在低函数评估次数下改善速度-质量权衡。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.26324 2026-05-27 cs.LG cs.AI cs.NA math.NA

Semigroup Consistency as a Diagnostic for Learned Physics Simulators

半群一致性作为学习型物理模拟器的诊断工具

Lennon J. Shikhman

机构 * Georgia Institute of Technology(佐治亚理工学院)

AI总结 提出归一化半群误差作为评估学习型物理模拟器时间组合和长程推演一致性的诊断指标,在热传导和Burgers动力学实验中验证其与推演退化正相关。

Comments 10 pages, 3 figures, 3 tables. Accepted to the AI4Physics Workshop at the 43rd International Conference on Machine Learning

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.17036 2026-05-27 cs.AI cs.LG cs.MA cs.SY eess.SY

Reliability and Effectiveness of Autonomous AI Agents in Supply Chain Management

自主AI代理在供应链管理中的可靠性与有效性

Carol Xuan Long, David Simchi-Levi, Feng Zhu, Huangyuan Su, Andre P. Calmon, Flavio P. Calmon

机构 * Harvard University(哈佛大学) MIT/Purdue(麻省理工学院/普渡大学) MIT(麻省理工学院) Harvard University/Kempner Institute(哈佛大学/凯普勒研究所) Georgia Tech(佐治亚理工学院)

AI总结 本文通过MIT啤酒游戏研究多级供应链中的自主生成式AI代理,发现模型能力是性能主导因素,但平均性能掩盖可靠性风险,并引入代理牛鞭效应,提出基于GRPO的后训练框架以提高可靠性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.21882 2026-05-27 cs.LG cs.AI

Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards

立场:具有可验证奖励的强化学习的隐藏成本与测量缺口

Fang Wu, Aaron Tu, Weihao Xuan, Heli Qi, Xu Huang, Qingcheng Zeng, Shayan Talaei, Yijia Xiao, Peng Xia, Xiangru Tang, Yuchen Zhuang, Yinxi Li, Bing Hu, Hanqun Cao, Wenqi Shi, Rui Yang, Nan Liu, Huaxiu Yao, Ge Liu, Li Erran Li, Amin Saberi, Naoto Yokoya, Jure Leskovec, Yejin Choi

机构 * Stanford University(斯坦福大学) UC Berkeley(加州大学伯克利分校) The University of Tokyo(东京大学) RIKEN AIP(理化学研究所AIP) Waseda University(早稻田大学) Georgia Tech(佐治亚理工学院) Northwestern University(西北大学) UCLA(加州大学洛杉矶分校) UNC Chapel Hill(北卡罗来纳大学教堂山分校) Yale University(耶鲁大学) University of Waterloo(滑铁卢大学) Independent Researcher(独立研究者) CUHK(香港中文大学) UT Southwestern Medical Center(西南医学中心) National University of Singapore(新加坡国立大学) UIUC(伊利诺伊大学厄巴纳-香槟分校) Amazon AWS AI(亚马逊AWS人工智能)

AI总结 本文指出,具有可验证奖励的强化学习(RLVR)在提升大语言模型性能时,常因预算不匹配、尝试膨胀和基准数据污染等混淆因素导致收益被高估,并提出了预算匹配饱和曲线、校准跟踪、法官鲁棒性测试和污染筛查等最低标准。

详情

展开后加载摘要…

URL PDF HTML 收藏
2306.13985 2026-05-27 stat.ML cs.AI cs.LG stat.ME

Robust Classification of High-Dimensional Data using Data-Adaptive Energy Distance

使用数据自适应能量距离的高维数据鲁棒分类

Jyotishka Ray Choudhury, Aytijhya Saha, Sarbojit Roy, Subhajit Dutta

机构 * Indian Statistical Institute , Kolkata, India(印度统计研究所,加尔各答,印度) School of Industrial and Systems Engineering, Georgia Institute of Technology , Atlanta, USA(工业与系统工程学院,佐治亚理工学院,美国亚特兰大) Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology , Saudi Arabia(计算机、电子和数学科学与工程系,国王阿卜杜勒·阿齐兹大学科学与技术学院,沙特阿拉伯) Applied Statistics Unit, Indian Statistical Institute , Kolkata, India(应用统计部,印度统计研究所,加尔各答,印度) Department of Mathematics and Statistics, Indian Institute of Technology Kanpur , India(数学与统计系,印度理工学院坎普尔分校,印度)

AI总结 针对高维低样本量数据,提出无调参、无矩条件的鲁棒分类器,在渐近条件下实现完美分类,并通过模拟和真实数据验证其优势。

Comments Published at the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), 2023

Journal ref In: ECML PKDD 2023: Research Track. Lecture Notes in Computer Science, vol 14173. Springer, Cham (2023)

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.00357 2026-05-27 cs.LG stat.ML

Neural Scaling Laws of Deep ReLU and Deep Operator Network: A Theoretical Study

深度ReLU和深度算子网络的神经缩放定律:一项理论研究

Hao Liu, Zecheng Zhang, Wenjing Liao, Hayden Schaeffer

机构 * Department of Mathematics, Hong Kong Baptist University(香港 Baptist 大学数学系) Department of ACMS, University of Notre Dame(Notre Dame 大学ACMS系) School of Mathematics, Georgia Institute of Technology(佐治亚理工学院数学系) Department of Mathematics, UCLA(加州大学洛杉矶分校数学系)

AI总结 本文通过分析深度算子网络的逼近误差和泛化误差,建立了量化神经缩放定律的理论框架,揭示了网络模型大小和训练数据大小与误差之间的关系,并推广到深度ReLU网络。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.26072 2026-05-26 cs.LG

Active Query Synthesis for Preference Learning

用于偏好学习的主动查询合成

Namrata Nadagouda, Nauman Ahad, Maegan Tucker, Mark A. Davenport

机构 * Georgia Institute of Technology(佐治亚理工学院) Gauss Labs(Gauss实验室)

AI总结 针对偏好学习中的查询反馈可靠性问题和池评估计算瓶颈,提出基于互信息最大化的连续空间主动查询合成框架Info-Synth,并扩展出两种有限池查询策略,在合成数据、文本摘要和机器人控制任务上验证了有效性。

Comments 27 pages, 12 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.25360 2026-05-26 cs.CL

Learning to Route Languages for Multilingual Policy Optimization

学习路由语言以实现多语言策略优化

Geyang Guo, Hiromi Wakaki, Yuki Mitsufuji, Alan Ritter, Wei Xu

机构 * Georgia Institute of Technology(佐治亚理工学院) Sony Group Corporation(索尼集团)

AI总结 提出语言路由策略优化(LRPO)框架,将语言作为可选变量,通过在线策略优化和可训练的语言路由器(多臂老虎机)自适应地选择语言,在固定预算下提升多语言训练信号的多样性和信息量,从而显著提高多语言性能。

Comments Accepted at ICML 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.06798 2026-05-26 cs.LG cs.DC stat.ML

NEST: Network- and Memory-Aware Device Placement For Distributed Deep Learning

NEST: 面向分布式深度学习的网络与内存感知设备放置

Irene Wang, Vishnu Varma Venkata, Arvind Krishnamurthy, Divya Mahajan

机构 * Georgia Institute of Technology(佐治亚理工学院) University of Washington(华盛顿大学)

AI总结 提出NEST框架,通过结构化动态规划统一模型并行、拓扑建模和内存可行性,在多种硬件和网络上实现高达2.43倍的吞吐量提升。

Comments Accepted to MLSys 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.24774 2026-05-26 cs.LG physics.comp-ph

Hermite-NGP: Gradient-Augmented Hash Encoding for Learning PDEs

Hermite-NGP:用于学习PDE的梯度增强哈希编码

Jinjin He, Zhiqi Li, Sinan Wang, Bo Zhu

机构 * Georgia Institute of Technology, Atlanta, GA, USA(佐治亚理工学院,亚特兰大,GA,美国)

AI总结 提出Hermite-NGP,一种梯度增强的多分辨率哈希编码,通过显式存储哈希网格顶点处的函数值和混合偏导数并利用Hermite插值实现解析梯度计算,从而快速准确地计算神经PDE求解器的空间导数,并引入多分辨率课程训练策略,在2D和3D PDE基准上实现高达约20倍误差降低和2-10倍收敛时间减少。

Comments Accepted by ICML 2026.Project page: https://jinjinhe2001.github.io/hermite-ngp/

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.24743 2026-05-26 cs.LG cs.AI

Bilevel Optimization of Synthetic Trajectories for Multi-Turn LLM Fine-Tuning

用于多轮LLM微调的合成轨迹的双层优化

Shresth Verma, Mauricio Tec, Cheol Woo Kim, Kai Wang, Milind Tambe

机构 * Harvard University(哈佛大学) Georgia Institute of Technology(佐治亚理工学院)

AI总结 提出BOOST双层优化框架,通过内层加权训练和外层轻量级重加权头学习,解决合成轨迹质量异质性导致的LLM多轮交互性能下降问题。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.24740 2026-05-26 cs.LG cs.GT

Reinforcement Learning for Reachability: Guaranteeing Asymptotic Optimality

可达性的强化学习:保证渐近最优性

Amogh Palasamudram, Jakub Svoboda, Suguman Bansal, Krishnendu Chatterjee

机构 * Institute of Science and Technology, Austria(奥地利科学与技术研究所) Georgia Institute of Technology, USA(美国佐治亚理工学院) Dartmouth College, USA(美国达特茅斯学院)

AI总结 针对可达性规格的强化学习,提出一种基于PAC学习的迭代方法,在无需已知MDP内部参数的情况下实现渐近最优策略,并通过实验验证收敛动态。

Comments Main text and appendix of work accepted in ICML 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.10250 2026-05-26 cs.LG

GeMPO: Generalized Measure Matching for Online Diffusion Reinforcement Learning

GeMPO:在线扩散强化学习的广义度量匹配

Haitong Ma, Chenxiao Gao, Tianyi Chen, Na Li, Bo Dai

机构 * Harvard University(哈佛大学) Georgia Institute of Technology(佐治亚理工学院)

AI总结 提出GeMPO框架,通过将扩散RL中的重加权从softmax推广到一般单调函数,并引入负重加权机制,以解决过贪策略和负样本利用不足的问题。

Comments 22 pages, 6 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.24345 2026-05-26 cs.LG

Evolving Robustness--Exploration Trade-off in Online Reinforcement Learning via Quantile Bayesian Risk MDPs

通过分位数贝叶斯风险MDP演化在线强化学习中的鲁棒性-探索权衡

Meichen Song, Yuhao Wang, Enlu Zhou

机构 * School of Industrial and Systems Engineering(工业与系统工程系) Georgia Institute of Technology(佐治亚理工学院)

AI总结 本文提出一种基于分位数贝叶斯风险MDP的自适应算法,通过动态调整分位数水平来平衡早期鲁棒性与后期探索,并证明了亚线性贝叶斯遗憾界。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.24311 2026-05-26 cs.RO

Terrain-Adaptive Grouser Wheel for Optimal Planetary Exploration: Design and Experimental Investigation

地形自适应履刺轮用于最优行星探测:设计与实验研究

Vincent Griffo, Yashwanth Kumar Nakka

机构 * Aerospace Robotics Lab, Daniel Guggenheim School of Aerospace Engineering, Georgia Institute of Technology(航空航天机器人实验室,丹尼尔·古根海姆航空航天工程学院,佐治亚理工学院)

AI总结 针对行星车在颗粒地形上的移动难题,提出一种可连续调节履刺高度的多模态轮,实验表明自适应部署可减少滑转30-58%,并提升行驶时间和能效达77.4%。

Comments Under Review

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.23977 2026-05-26 cs.CL cs.SD eess.AS

A Multi-Probe Audit of Clinical-Interview Depression Detection Benchmarks

临床访谈抑郁症检测基准的多探针审计

Takehiro Ishikawa, Jon Duke

机构 * College of Computing, Georgia Institute of Technology(佐治亚理工学院计算机学院) Georgia Tech Research Institute, Georgia Institute of Technology(佐治亚理工学院研究 institute)

AI总结 通过四个互补探针审计临床访谈抑郁症检测基准,发现评估协议缺陷、排行榜不可靠、跨域泛化弱以及文本与音频模态对症状密度的敏感性差异。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.03955 2026-05-26 cs.AI cs.MA

AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent

AgentArk:将多智能体智能蒸馏到单个LLM智能体中

Yinyi Luo, Yiqiao Jin, Weichen Yu, Mengqi Zhang, Srijan Kumar, Xiaoxiao Li, Weijie Xu, Xin Chen, Jindong Wang

机构 * Carnegie Mellon University(卡内基梅隆大学) William & Mary(威廉与玛丽学院) Georgia Institute of Technology(佐治亚理工学院) Amazon(亚马逊) University of British Columbia(不列颠哥伦比亚大学)

AI总结 提出AgentArk框架,通过三种分层蒸馏策略将多智能体系统的交互动态蒸馏到单个模型权重中,使单个智能体具备多智能体的推理和自校正能力,同时保持计算效率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.11428 2026-05-26 cs.LG

Diagnosing Failure Modes of Neural Operators Across Diverse PDE Families

诊断不同PDE族中神经算子的失败模式

Lennon Shikhman

机构 * Georgia Institute of Technology(佐治亚理工学院)

AI总结 本文提出一个标准化压力测试框架,通过在不同PDE族上测试FNO、DeepONet和CNO三种架构,发现分布内准确率不能可靠预测鲁棒性,且失败模式依赖于架构和PDE族的组合。

Comments Published in Transactions on Machine Learning Research. 17 pages, 7 figures, 1 table

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.20539 2026-05-26 cs.AI cs.CL

PathWise: Planning through World Model for Automated Heuristic Design via Self-Evolving LLMs

PathWise:通过世界模型规划实现基于自进化LLM的自动启发式设计

Oguzhan Gungordu, Siheng Xiong, Faramarz Fekri

机构 * Georgia Institute of Technology(佐治亚理工学院)

AI总结 提出PathWise多智能体推理框架,将启发式生成建模为基于蕴含图的序列决策过程,通过策略智能体、世界模型智能体和评论智能体的协作实现状态感知规划,在组合优化问题上收敛更快、泛化更强。

Comments Accepted to ICML 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.23193 2026-05-25 cs.HC cs.CL cs.CY cs.MA

CultivAgents: Cultivating Relationship-Centered Multi-Agent Systems for Personalized Gardening

CultivAgents:培育以关系为中心的多智能体系统以实现个性化园艺

Yiyang Wang, Moeiini Reilly, Britney Johnson, Kefei Yan, Alex Cabral, Josiah Hester

机构 * Georgia Institute of Technology(佐治亚理工学院) Massachusetts Institute of Technology(麻省理工学院)

AI总结 提出 CultivAgents,一个基于关怀伦理、协调经验、环境和民族植物学三个专业智能体的多智能体系统,为社区园丁提供个性化、社会文化背景化的园艺支持,并通过混合方法研究验证其有效性。

Comments Preprint, 9 pages. Website: https://hello-diana.github.io/CultivAgents/

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.23070 2026-05-25 cs.CV

Flow Mismatching: Unsupervised Anomaly Detection via Velocity Discrepancies in Flow Matching Models

Flow Mismatching: 通过流匹配模型中的速度差异进行无监督异常检测

Shengzhe Chen, Mehrdad Moradi, Kamran Paynabar, Hao Yan

机构 * Arizona State University(亚利桑那州立大学) Georgia Institute of Technology(佐治亚理工学院)

AI总结 提出Flow Mismatching方法,利用正常数据训练的流匹配模型在测试图像路径上的预测速度与几何速度的差异进行无监督异常检测,无需重建、测试时优化或额外校准。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.23043 2026-05-25 cs.CL stat.ML

HawkesLLM: Semantic Uncertainty Propagation in Agentic Text Simulation

HawkesLLM:智能体文本模拟中的语义不确定性传播

Zewei Deng, Tinghan Ye, Liyan Xie

机构 * Department of Industrial and Systems Engineering, University of Minnesota(工业与系统工程系,明尼苏达大学) H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology(H. Milton Stewart工业与系统工程学院,佐治亚理工学院)

AI总结 提出HawkesLLM框架,通过多变量Hawkes过程建模时间影响与文本生成分离,解决智能体文本模拟中语义不确定性路径依赖问题,在GDELT新闻级联案例中提升后期语义对齐。

Comments 10 pages, 4 figures, Accepted at the ICML 2026 Workshop on Statistical Frameworks for Uncertainty in Agentic Systems

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.21906 2026-05-25 cs.CV

Universal CT Representations from Anatomy to Disease Phenotype through Agglomerative Pretraining

从解剖到疾病表型的通用CT表示:通过聚合预训练

Yuheng Li, Yuan Gao, Haoyu Dong, Yuxiang Lai, Shansong Wang, Mojtaba Safari, James E. Baciak, Xiaofeng Yang

机构 * Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology and Emory University(沃森·H·库勒生物医学工程系,佐治亚理工学院和埃默里大学) Department of Radiation Oncology and Winship Cancer Institute, Emory University(放射肿瘤学系和Winship癌症研究所,埃默里大学) Department of Electrical and Computer Engineering, Duke University(电气与计算机工程系,杜克大学) Department of Computer Science and Informatics, Emory University(计算机科学与信息学系,埃默里大学) Department of Materials Science & Engineering, Nuclear Engineering Program, University of Florida(材料科学与工程系、核工程项目,佛罗里达大学)

AI总结 提出FlexiCT系列CT基础模型,通过三阶段聚合连续预训练(二维轴向、三维解剖、报告引导语义对齐)统一CT分析,在分割、分类、配准、视觉语言理解和临床检索等任务上达到或超越专用模型,并捕获与肿瘤分期相关的影像特征。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.11679 2026-05-25 cs.CV

Towards Brain MRI Foundation Models for the Clinic: Findings from the FOMO25 Challenge

面向临床的大脑MRI基础模型:来自FOMO25挑战赛的发现

Asbjørn Munk, Stefano Cerri, Vardan Nersesjan, Christian Hedeager Krag, Jakob Ambsdorf, Pablo Rocamora García, Julia Machnio, Peirong Liu, Suhyun Ahn, Nasrin Akbari, Yasmina Al Khalil, Kimberly Amador, Sina Amirrajab, Tal Arbel, Meritxell Bach Cuadra, Ujjwal Baid, Bhakti Baheti, Jaume Banus, Kamil Barbierik, Christoph Brune, Yansong Bu, Baptiste Callard, Yuhan Chen, Cornelius Crijnen, Corentin Dancette, Peter Drotar, Prasad Dutande, Nils D. Forkert, Saurabh Garg, Jakub Gazda, Matej Gazda, Benoît Gérin, Partha Ghosh, Weikang Gong, Pedro M. Gordaliza, Sam Hashemi, Tobias Heimann, Fucang Jia, Jiexin Jiang, Emily Kaczmarek, Chris Kang, Seung Kwan Kang, Mohammad Khazaei, Julien Khlaut, Petros Koutsouvelis, Jae Sung Lee, Yuchong Li, Mengye Lyu, Mingchen Ma, Anant Madabhushi, Klaus H. Maier-Hein, Pierre Manceron, Andrés Martínez Mora, Moona Mazher, Felix Meister, Nataliia Molchanova, Steven A. Niederer, Leonard Nürnberg, Jinah Park, Abdul Qayyum, Jonas Richiardi, Antoine Saporta, Branislav Setlak, Ning Shen, Justin Szeto, Constantin Ulrich, Puru Vaish, Vibujithan Vigneshwaran, Leroy Volmer, Zihao Wang, Siqi Wei, Anthony Winder, Jelmer M. Wolterink, Maxence Wynen, Chang Yang, Si Young Yie, Mostafa Mehdipour Ghazi, Akshay Pai, Espen Jimenez Solem, Sebastian Nørgaard Llambias, Mikael Boesen, Michael Eriksen Benros, Juan Eugenio Iglesias, Mads Nielsen

机构 * organization= Department of Computer Science, University of Copenhagen , city= Copenhagen , country= Denmark organization= Pioneer Centre for AI , city= Copenhagen , country= Denmark organization= Copenhagen Research Centre for Biological Precision Psychiatry, Mental Health Centre Copenhagen, Copenhagen University Hospital , region= Capital Region of Denmark , city= Copenhagen , country= Denmark organization= Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital Harvard Medical School , city= Boston , state= Massachusetts , country= USA Artificial Intelligence Laboratory, Massachusetts Institute of Technology , city= Boston , state= Massachusetts , country= USA organization= Johns Hopkins University , city= Baltimore , state= Maryland , country= USA organization= Radiological AI Testcenter (RAIT) , region= Capital Region of Denmark , city= Copenhagen , country= Denmark organization= Copenhagen University Hospital, Rigshospitalet , region= Capital Region of Denmark , city= Copenhagen , country= Denmark organization= Copenhagen University Hospital, Bispebjerg \& Frederiksberg Hospital , region= Capital Region of Denmark , city= Copenhagen , country= Denmark organization= Department of Clinical Medicine, Faculty of Health Medical Sciences, University of Copenhagen , city= Copenhagen , country= Denmark organization= Division of Medical Image Computing, German Cancer Research Center (DKFZ) , city= Heidelberg , country= Germany organization= University of British Columbia , city= Vancouver , state= British Columbia , country= Canada organization= Hawkes Institute, Department of Computer Science, University College London , city= London , country= United Kingdom Lung Institute, Faculty of Medicine, Imperial College London , city= London , country= United Kingdom organization= Department of Applied Mathematics, Technical Medical Centre, University of Twente , city= Enschede , country= Netherlands organization= IISLAB, Technical University of Košice , city= Košice , country= Slovakia organization= 2nd Department of Internal Medicine, Pavol Jozef Safarik University L Pasteur University Hospital , city= Košice , country= Slovakia organization= Fudan University , city= Shanghai , country= China organization= Shenzhen Technology University , city= Shenzhen , country= China organization= Department of Radiology, Lausanne University Hospital University of Lausanne , city= Lausanne , country= Switzerland organization= Louvain Neuroinflammation Imaging Lab (NIL), Université Catholique de Louvain , city= Brussels , country= Belgium organization= University of Applied Sciences organization= CIBM Center for Biomedical Imaging , city= Lausanne , country= Switzerland organization= Department of Radiation Oncology (Maastro), GROW Research Institute for Oncology Reproduction, Maastricht University Medical Centre+ , city= Maastricht , country= The Netherlands organization= Department of Biomedical Engineering, Medical Image Analysis, Eindhoven University of Technology , city= Eindhoven , country= The Netherlands organization= Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences , city= Shenzhen , country= China organization= McGill University Mila - Quebec AI Institute , city= Montreal , country= Canada organization= Hotchkiss Brain Institute Department of Radiology, University of Calgary , city= Calgary , state= Alberta , country= Canada organization= Department of Radiology, University of Calgary , city= Calgary , state= Alberta , country= Canada organization= Alberta Children's Hospital Research Institute, Department of Clinical Neuroscience, University of Calgary , city= Calgary , state= Alberta , country= Canada organization= The Wallace H. Coulter Department of Biomedical Engineering, Georgia Tech Emory University , city= Atlanta , state= Georgia , country= USA organization= SGGS College of Engineering organization= Seoul National University , city= Seoul , country= South Korea organization= The D-Lab, Department of Precision Medicine, GROW Research Institute for Oncology Reproduction, Maastricht University , city= Maastricht , country= The Netherlands organization= Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School , city= Boston , state= Massachusetts , country= USA Nuclear Medicine, CARIM \& GROW, Maastricht University , city= Maastricht , country= The Netherlands organization= Department of Radiation Oncology, Dana-Farber Cancer Institute, Brigham Women’s Hospital, Harvard Medical School , city= Boston , state= Massachusetts , country= USA Learning Group, Heidelberg University Hospital , city= Heidelberg , country= Germany

AI总结 针对临床脑MRI数据异质且标注成本高的问题,FOMO25挑战赛通过自监督预训练(FOMO60K数据集)评估了16个团队的基础模型,发现自监督预训练能提升域迁移泛化性,但不同任务需不同预训练目标,且模型规模扩展收益有限。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.22875 2026-05-25 cs.AI cs.LG

RMA: an Agentic System for Research-Level Mathematical Problems

RMA:一个面向研究级数学问题的智能体系统

Zelin Zhao, Bo Yuan, Jaemoo Choi, Yongxin Chen

机构 * Georgia Institute of Technology(佐治亚理工学院)

AI总结 提出Research Math Agents (RMA)框架,通过多角色多轮协作的智能体工作流,在First Proof基准上解决80%的研究级数学问题,优于GPT-5.2R等基线。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.06597 2026-05-22 cs.CL cs.AI cs.LG

UniSD: Towards a Unified Self-Distillation Framework for Large Language Models

UniSD:面向大语言模型的统一自蒸馏框架

Yiqiao Jin, Yiyang Wang, Lucheng Fu, Yijia Xiao, Yinyi Luo, Haoxin Liu, B. Aditya Prakash, Josiah Hester, Jindong Wang, Srijan Kumar

机构 * Georgia Institute of Technology(佐治亚理工学院) University of California, Los Angeles(加州大学洛杉矶分校) Carnegie Mellon University(卡内基梅隆大学) William & Mary(威廉与玛丽大学)

AI总结 本文提出UniSD框架,系统研究自蒸馏方法,通过整合多种机制提升监督可靠性、表征对齐和训练稳定性,从而在多个基准和模型上验证自蒸馏的有效性,并构建出性能最优的UniSDfull流水线。

Comments Website: https://unifiedsd.github.io/ Code: https://github.com/Ahren09/UniSD

详情

展开后加载摘要…

URL PDF HTML 收藏