arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

University of Southern California(南加州大学)

2026-08-11 至 2026-08-11 共收录 4
2608.08284 2026-08-11 cs.AI 新提交

Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders

表面上公平?对LLM推荐器的隐藏输出公平性差距进行基准测试

Chan Aristella Lu, Arya Fayyazi, Junhao Zhang, Saeid Shokoufa, Yue Xing, Zhen Xiang, Kyu Hyung Lee, Mehdi Kamal, Massoud Pedram

机构 * University of Georgia(佐治亚大学) University of Southern California(南加州大学) Carnegie Mellon University(卡内基梅隆大学) Michigan State University(密歇根州立大学)

AI总结 该研究提出首个联合评估LLM推荐器可观测输出与隐藏表示公平性的基准FairGap,发现二者存在根本张力,现有框架无法诊断。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.22357 2026-08-11 cs.CL cs.CV cs.LG 版本更新

ORBIT: Training-Free Multi-Attribute Behavioral Steering via Orthogonal Subspace Rotation

ORBIT: 通过正交子空间旋转实现无训练的多属性行为引导

Narges Ghasemi, Amir Ziashahabi, Salman Avestimehr, Jonathan May

机构 * Information Sciences Institute, University of Southern California(南加州大学信息科学研究所) Department of Electrical and Computer Engineering, University of Southern California(南加州大学电气与计算机工程系)

AI总结 提出ORBIT方法,利用奇异值分解构建联合子空间并施加单一旋转,实现无训练的多属性行为引导,平衡多个属性并保持输出连贯性。

Comments v2: Updated technical details and added supplementary evaluations

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.17640 2026-08-11 eess.AS cs.SD 版本更新

End-to-End Joint ASR and Speaker Role Diarization with Child-Adult Interactions

端到端联合语音识别与说话人角色辨识的儿童-成人互动

Anfeng Xu, Tiantian Feng, Somer Bishop, Catherine Lord, Shrikanth Narayanan

机构 * Viterbi School of Engineering, University of Southern California, US(维特比工程学院,南加州大学) Weill Institute for Neurosciences, University of California, San Francisco, US(韦尔神经科学研究所,旧金山大学) David Geffen School of Medicine, University of California, Los Angeles, US(大卫·盖芬医学院,洛杉矶大学)

AI总结 本文提出了一种端到端联合建模框架,用于在大规模上生成可靠的儿童-成人互动转录,通过联合建模语音识别和说话人角色辨识,提高了转录的准确性和效率。

Comments Published in IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.19112 2026-08-11 cs.RO math.DS 版本更新

Analysis and experiments of the dissipative Twistcar: direction reversal and asymptotic approximations

耗散型Twistcar的分析与实验:方向反转及渐近近似

Rom Levy, Ari Dantus, Zitao Yu, Yizhar Or

机构 * Department of Mechanical Engineering, Technion - Israel Institute of Technology(机械工程系,技术学院-以色列理工学院) Department of Aerospace and Mechanical Engineering, University of Southern California(航空航天与机械工程系,南加州大学)

AI总结 本研究将耗散纳入Twistcar的双连杆模型,推导其小幅稳态周期动力学的渐近表达式,构建可调节质心的机器人原型验证方向反转现象,并通过参数拟合提升实验吻合度。

Comments The paper has been accepted for publication at Multibody Systems Dynamics (Springer Nature), August 2026

详情

展开后加载摘要…

URL PDF HTML 收藏