13 papers
When Does More Correct Data Hurt? Insertion-Stability and the Limits of Dimension-Based Theory
Joseph Sankoorikal Johny
Adding data known to be correct ought to be safe. Not always. Larsen, Pabbaraju and Shetty model the failure with a monotone adversary, which reads an i.i.d. training sample and ma…
Scene2Sound: Auditory-Grounded Soundscape Generation for 3D Gaussian Worlds
Masaki Yoshida, Ren Togo, Takahiro Ogawa +1
3D Gaussian Splatting (3DGS) turns captured or generated imagery into photorealistic 3D world simulations that users can freely explore, yet these worlds remain silent. Because exi…
L2R: Low-Rank and Lipschitz-Controlled Routing for Mixture-of-Experts
Minghao Yang, Ren Togo, Guang Li +2
Mixture-of-Experts (MoE) models scale neural networks by conditionally activating a small subset of experts, where the router plays a central role in determining expert specializat…
Personalized Longitudinal Medical Report Generation via Temporally-Aware Federated Adaptation
He Zhu, Ren Togo, Takahiro Ogawa +8
Longitudinal medical report generation is clinically important yet remains challenging due to strict privacy constraints and the evolving nature of disease progression. Although fe…
Foreground-Aware Dataset Distillation via Dynamic Patch Selection
Longzhen Li, Guang Li, Ren Togo +3
In this paper, we propose a foreground-aware dataset distillation method that enhances patch selection in a content-adaptive manner. With the rising computational cost of training…
Dual-Model Weight Selection and Self-Knowledge Distillation for Medical Image Classification
Ayaka Tsutsumi, Guang Li, Ren Togo +3
We propose a novel medical image classification method that integrates dual-model weight selection with self-knowledge distillation (SKD). In real-world medical settings, deploying…