過去のお知らせ
2026年10月26-29日に兵庫県神戸市にて開催されるコンシューマエレクトロニクス分野の国際会議IEEE Global Conference on Consumer Electronics 2026 (GCCE2026)に、当研究室より投稿していた以下の14件の論文が採択されました！
[1] Bincheng Peng, Guang Li, Ping Liu, Takahiro Ogawa, Miki Haseyama, “Efficient linear-probe dataset distillation for pre-trained vision models”
[2] Ge Tian, Guang Li, Takahiro Ogawa, Miki Haseyama, “Adaptive multi-level response matching for point cloud dataset distillation”
[3] Seiya Kidoguchi, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, “Instruction-tuned vision language model for bridge inspection with reason-based prompts”
[4] Ibuki Kameya, Tasuku Nakajima, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, “A privacy-preserving unlearning framework based on pixel-level encryption”
[5] Tatsuki Yamada, Ryota Goka, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, “Does side really matter? Investigating left-right bias in skeleton-based human action recognition”
[6] Toma Onozuka, Koshiro Toishi, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, “Mitigating concept bleed-through in continual personalized image generation via latent space-based target selection”
[7] Kentaro Oishi, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Application of deep autoencoding Gaussian mixture model for anomaly detection in hyperspectral analysis of rubber materials”
[8] Akira Hasegawa, Kenta Kubota, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Towards low-power time-series anomaly detection with spike-based variational autoencoder”
[9] Akari Maeda, Masaki Yoshida, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Spatial audio reproduction from 3D Gaussian splatting scenes via mesh conversion and mesh-based acoustic simulation”
[10] Takuya Kinoshita, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, “Quantifying task difficulty for LLMs based on reasoning trajectories”
[11] Shin Kawamura, Tatsuki Seino, Naoki Saito, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Prompt refinement for vision-language-action models under incomplete instructions for robot control”
[12] Yuki Iwasa, Keigo Sakurai, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Ranking refinement with context-dependent acoustic preference for music recommendation”
[13] Ryuki Unno, Koshi Watanabe, Keigo Sakurai, Takahiro Ogawa, Miki Haseyama, “Impact of expert-following strategies in financial asset recommendation”
[14] Genki Masuyama, Keigo Sakurai, Ren Togo, Takahiro Ogawa, Miki Haseyama, “Local temporal onset density control in symbolic music arrangement via sparse autoencoders”