| title |
|---|
Home |
{% include figure.html img="colorai.png" alt="colorai logo" width="60%" %}
Many of the recent advancements in AI are due to exploiting structured low-rank representations, from low-rank tensor factorizations (Kolda and Bader 2009; Kossaifi et al. 2019) for scaling large language models (LLMs), e.g., via adapters (Hu et al. 2021) or structured matrices (Dao et al. 2022); the diffusion of compact polynomial representations as powerful inductive biases for deep learning architectures (Cheng et al. 2024); the emergence of probabilistic circuits to provide tractable probabilistic inference with guarantees (Loconte et al. 2024; Choi et al. 2020) and reliable neuro-symbolic AI (Ahmed et al. 2022); and the wide application of tensor networks to solve and accelerate physics-related problems (Biamonte and Bergholm 2017) and quantum computing (Orus 2019).
"How are all these representations related to each others? and how can we transfer knowledge across communities?"
We will try to answer the above questions in our day workshop at the Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI-25). The workshop will be held at the Pennsylvania Convention Center in Philadelphia, Pennsylvania, USA, March 3-4, 2025.
See our call for papers.
- [15th Oct 2024] Nadav, Guillame, Yannis and Andrew confirmed to be speakers!
- [25th Sep 2024] Openreview is open to receive submissions!
- [20th Sep 2024] Website is on!
- Kolda and Bader 2009 - Tensor decompositions and applications
- Hu et al. 2021 - LoRA: Low-Rank Adaptation of Large Language Models
- Loconte et al. 2024 - What is the Relationship between Tensor Factorizations and Circuits (and How Can We Exploit it)?
- Dao et al. 2022 - Monarch: Expressive Structured Matrices for Efficient and Accurate Training
- Kossaifi et al. 2019 - Tensorly: Tensor learning in python
- Cheng et al. 2024 - Multilinear Operator Networks
- Choi et al. 2020 - Probabilistic Circuits: A Unifying Framework for Tractable Probabilistic Models
- Ahmed et al. 2022 - Semantic Probabilistic Layers for Neuro-Symbolic Learning
- Biamonte and Bergholm 2017 - Tensor Networks in a Nutshell
- Orus 2019 - Tensor networks for complex quantum systems
Last build date: {{ site.time | date: "%Y-%m-%d" }}.