6 papers
Structured Pruning of Large Language Models via Power Transformation and Sign-Preserving Score Aggregation with Adaptive Feature Retention
Ryota Kobayashi, Tsubasa Hirakawa, Takayoshi Yamashita +4
This paper proposes an improved structured pruning method for large language models (LLMs) that addresses key challenges in adapting Adaptive Feature Retention (AFR), an unstructur…
P2GS: Physical Prior-guided Gaussian Splatting for Photometrically Consistent Urban Reconstruction
Kota Shimomura, Hidehisa Arai, Tsubasa Takahashi +2
3D Gaussian Splatting (3DGS) has recently emerged as a powerful explicit representation enabling fast, high-fidelity rendering, making it a promising foundation for closed-loop sim…
Mix-Geneformer: Unified Representation Learning for Human and Mouse scRNA-seq Data
Yuki Nishio, Takayoshi Yamashita, Keita Ito +2
Single-cell RNA sequencing (scRNA-seq) enables single-cell transcriptomic profiling, revealing cellular heterogeneity and rare populations. Recent deep learning models like Genefor…
DeBiFormer: Vision Transformer with Deformable Agent Bi-level Routing Attention
Nguyen Huu Bao Long, Chenyu Zhang, Yuzhi Shi +4
Vision Transformers with various attention modules have demonstrated superior performance on vision tasks. While using sparsity-adaptive attention, such as in DAT, has yielded stro…
Nearest Neighbor Future Captioning: Generating Descriptions for Possible Collisions in Object Placement Tasks
Takumi Komatsu, Motonari Kambara, Shumpei Hatanaka +5
Domestic service robots (DSRs) that support people in everyday environments have been widely investigated. However, their ability to predict and describe future risks resulting fro…
Layer-Wise Relevance Propagation with Conservation Property for ResNet
Seitaro Otsuki, Tsumugi Iida, Félix Doublet +4
The transparent formulation of explanation methods is essential for elucidating the predictions of neural networks, which are typically black-box models. Layer-wise Relevance Propa…