Publications

56 results for Seiji Takeda

Controllable Molecular Generation via Sparse Autoencoders and Feature-Guided Latent Manipulation
- - Lisa Hamada
  - Indra Priyadarsini S
  - et al.
- 2026
- MRS Spring 2026
Conference paper
Enabling Accurate and Interpretable Property Prediction with TDiMS in Large Molecules
- - Lisa Hamada
  - Akihiro Kishimoto
  - et al.
- 2025
- NeurIPS 2025
Workshop paper
Learning Resilient Molecular Representations with Dynamic Multi-Modal Fusion
- - Indra Priyadarsini S
  - Seiji Takeda
  - et al.
- 2025
- NeurIPS 2025
Workshop paper
Capturing Long-Range Intramolecular Interactions with TDiMS for Interpretable Property Prediction
- - Lisa Hamada
  - Akihiro Kishimoto
  - et al.
- 2025
- NeurIPS 2025
Workshop paper
A Self-Supervised Framework for Robust Multi-Modal Molecular Representation Learning
- - Indra Priyadarsini S
  - Seiji Takeda
  - et al.
- 2025
- NeurIPS 2025
Workshop paper
Leveraging Large Language Models for Suitability Assessment of Electrolytes for Rechargeable Batteries
- - Sina Asuka Klampt
  - Seiji Takeda
  - et al.
- 2025
- MRS Fall Meeting 2025
Conference paper
A Synthetic Data Generation Framework with Chain-of-Thought Reasoning
- - Indra Priyadarsini S
  - Seiji Takeda
  - et al.
- 2025
- MRS Fall Meeting 2025
Conference paper
Interpretable Molecular Modeling via LLM Agents with Chain-of-Thought Reasoning
- - Seiji Takeda
  - Indra Priyadarsini S
  - et al.
- 2025
- MRS Fall Meeting 2025
Talk
Dynamic Multimodal Fusion for Robust Molecular Representation Learning
- - Indra Priyadarsini S
  - Seiji Takeda
  - et al.
- 2025
- ACS Fall 2025
Conference paper
Multi-View Mixture-of-Experts for predicting molecular properties using SMILES, SELFIES, and graph-based representations
- - Eduardo Almeida Soares
  - Victor Yukio Shirasuna
  - et al.
- 2025
- Machine Learning: Science and Tech.
Paper