Tootfinder

Affine quantum Schur algebras and $\imath$quantum groups with three parameters
Li Luo, Xirui Yu
https://arxiv.org/abs/2509.23559 https://arxiv.org/pdf/2509…

Affine quantum Schur algebras and $\imath$quantum groups with three parameters
We study the affine quantum Schur algebras corresponding to the affine Hecke algebras of type C with three parameters. Multiplication formulas for semisimple generators are derived for these algebras. We prove that they admit a stabilization property in the sense of Beilinson-Lusztig-MacPherson, by which we construct quasi-split $\imath$quantum groups of affine type AIII with three parameters. Upon specialization of parameters, we recover some known multiplication formulas for affine quantum Sc…

Dirichlet-Prior Shaping: Guiding Expert Specialization in Upcycled MoEs
Leyla Mirvakhabova, Babak Ehteshami Bejnordi, Gaurav Kumar, Hanxue Liang, Wanru Zhao, Paul Whatmough
https://arxiv.org/abs/2510.01185

Dirichlet-Prior Shaping: Guiding Expert Specialization in Upcycled MoEs
Upcycling pre-trained dense models into sparse Mixture-of-Experts (MoEs) efficiently increases model capacity but often suffers from poor expert specialization due to naive weight replication. Our analysis reveals that upcycled MoEs, even with conventional regularization, exhibit low-confidence, weakly differentiated routing, hindering performance. We introduce Dirichlet-Prior Shaping Loss (DPSL), a novel router regularization technique that directly shapes routing probability distributions by …

The Five Safes as a Privacy Context
James Bailie, Ruobin Gong
https://arxiv.org/abs/2510.05803 https://arxiv.org/pdf/2510.05803

The Five Safes as a Privacy Context
The Five Safes is a framework used by national statistical offices (NSO) for assessing and managing the disclosure risk of data sharing. This paper makes two points: Firstly, the Five Safes can be understood as a specialization of a broader concept $\unicode{x2013}$ contextual integrity $\unicode{x2013}$ to the situation of statistical dissemination by an NSO. We demonstrate this by mapping the five parameters of contextual integrity onto the five dimensions of the Five Safes. Secondly, the Fiv…

UniShield: An Adaptive Multi-Agent Framework for Unified Forgery Image Detection and Localization
Qing Huang, Zhipei Xu, Xuanyu Zhang, Jian Zhang
https://arxiv.org/abs/2510.03161

UniShield: An Adaptive Multi-Agent Framework for Unified Forgery Image Detection and Localization
With the rapid advancements in image generation, synthetic images have become increasingly realistic, posing significant societal risks, such as misinformation and fraud. Forgery Image Detection and Localization (FIDL) thus emerges as essential for maintaining information integrity and societal security. Despite impressive performances by existing domain-specific detection methods, their practical applicability remains limited, primarily due to their narrow specialization, poor cross-domain gen…

Quaternionic families of Heegner points and $p$-adic $L$-functions
Matteo Longo, Paola Magrone, Eduardo Rocha Walchek
https://arxiv.org/abs/2510.04306 https://

Quaternionic families of Heegner points and $p$-adic $L$-functions
Following up a previous article of the authors which studies the interpolation of certain anticyclotomic $p$-adic $L$-functions associated to quaternionic modular forms in a Hida family, we extend the work of F. Castella on the interpolation and specialization of big Heegner points to the quaternionic setting. We prove an explicit reciprocity law relating the big $p$-adic $L$-function to the big Heegner points in this quaternionic setting.

Mitigating Forgetting in Low Rank Adaptation
Joanna Sliwa, Frank Schneider, Philipp Hennig, Jose Miguel Hernandez-Lobato
https://arxiv.org/abs/2512.17720 https://arxiv.org/pdf/2512.17720 https://arxiv.org/html/2512.17720
arXiv:2512.17720v1 Announce Type: new
Abstract: Parameter-efficient fine-tuning methods, such as Low-Rank Adaptation (LoRA), enable fast specialization of large pre-trained models to different downstream applications. However, this process often leads to catastrophic forgetting of the model's prior domain knowledge. We address this issue with LaLoRA, a weight-space regularization technique that applies a Laplace approximation to Low-Rank Adaptation. Our approach estimates the model's confidence in each parameter and constrains updates in high-curvature directions, preserving prior knowledge while enabling efficient target-domain learning. By applying the Laplace approximation only to the LoRA weights, the method remains lightweight. We evaluate LaLoRA by fine-tuning a Llama model for mathematical reasoning and demonstrate an improved learning-forgetting trade-off, which can be directly controlled via the method's regularization strength. We further explore different loss landscape curvature approximations for estimating parameter confidence, analyze the effect of the data used for the Laplace approximation, and study robustness across hyperparameters.
toXiv_bot_toot

The Social Cost of Intelligence: Emergence, Propagation, and Amplification of Stereotypical Bias in Multi-Agent Systems
Thi-Nhung Nguyen, Linhao Luo, Thuy-Trang Vu, Dinh Phung
https://arxiv.org/abs/2510.10943

The Social Cost of Intelligence: Emergence, Propagation, and Amplification of Stereotypical Bias in Multi-Agent Systems
Bias in large language models (LLMs) remains a persistent challenge, manifesting in stereotyping and unfair treatment across social groups. While prior research has primarily focused on individual models, the rise of multi-agent systems (MAS), where multiple LLMs collaborate and communicate, introduces new and largely unexplored dynamics in bias emergence and propagation. In this work, we present a comprehensive study of stereotypical bias in MAS, examining how internal specialization, underlyi…

Assistant/Associate Professor of Church History
https://ift.tt/dwEeLxp
Fuller Theological Seminary School of Mission and Theology Tenure-Track Faculty Series Position…
via Input 4 RELCFP htt…

Assistant/Associate Professor of Church History
https://ift.tt/H09eVyQ
Fuller Theological Seminary School of Mission and Theology Tenure-Track Faculty Series Position…
via Input 4 RELCFP htt…

Assistant/Associate Professor of Church History
https://ift.tt/YSC5aXi
Fuller Theological Seminary School of Mission and Theology Tenure-Track Faculty Series Position…
via Input 4 RELCFP htt…

Assistant/Associate Professor of Church History
https://ift.tt/mOH8hKA
Fuller Theological Seminary School of Mission and Theology Tenure-Track Faculty Series Position…
via Input 4 RELCFP htt…