革新知能統合研究センター

第39回全米人工知能学会（AAAI-25）にて、ワークショップ「CoLoRAI – Connecting Low-Rank Representations in AI」を開催いたします。本ワークショップは、2025年3月4日に米国ペンシルベニア州フィラデルフィアのペンシルベニア・コンベンション・センターにて開催されます。テンソル学習チームのChao Li研究員がオーガナイザーを務めています。

• 日時：2025年3月4日・5日　時間は未定
• 会場：ペンシルベニア・コンベンション・センター（米国ペンシルベニア州フィラデルフィア）
• 論文投稿締切：2024年11月22日
• Topics of interest
  Topics of interest include, but are not limited to:

1. low-rank structures to speed up computation of large ML systems such as adaptors in LLMs and structured computational graphs
2. circuit representations for reliable and efficient probabilistic reasoning and learning with applications to trustworthy ML such as reliable neuro-symbolic AI
3. tensorial architecture design in deep learning such as polynomial representations that have emerged as a strong-performing alternative to the standard neural network paradigm
4. tensor networks for quantum and physics-inspired computing to solve variational inference, PDEs and inverse problems
5. theory of matrix and tensor factorization methods and their optimization in sketching, compression and tensor completion
6. expressivity of tensor representations including exponential lower bounds of matrix ranks and circuit sizes and sample complexity of learned representations
7. applications of low-rank representations in AI-related fields such as data and model compression, multimodal fusion, and model interpretability.

※詳細はウエブサイトをご覧ください
CoLoRAI