pliang279 / PIDLinks
[NeurIPS 2023, ICMI 2023] Quantifying & Modeling Multimodal Interactions
☆84Updated last year
Alternatives and similar repositories for PID
Users that are interested in PID are comparing it to the libraries listed below
Sorting:
- [NeurIPS 2023] Factorized Contrastive Learning: Going Beyond Multi-view Redundancy☆74Updated 2 years ago
- [ICLR 2023] MultiViz: Towards Visualizing and Understanding Multimodal Models☆98Updated last year
- [NeurIPS 2024 Spotlight] Code for the paper "Flex-MoE: Modeling Arbitrary Modality Combination via the Flexible Mixture-of-Experts"☆67Updated 6 months ago
- Code for the paper "Post-hoc Concept Bottleneck Models". Spotlight @ ICLR 2023☆89Updated last year
- CVPR 2023: Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification☆105Updated last year
- [T-PAMI] A curated list of self-supervised multimodal learning resources.☆272Updated last year
- Official Implementation of "Geometric Multimodal Contrastive Representation Learning" (https://arxiv.org/abs/2202.03390)☆28Updated 11 months ago
- [ICLR 23] A new framework to transform any neural networks into an interpretable concept-bottleneck-model (CBM) without needing labeled c…☆126Updated last year
- Code for the paper Visual Explanations of Image–Text Representations via Multi-Modal Information Bottleneck Attribution☆63Updated last year
- Implementation of FuseMoE for FlexiModal Fusion, NeurIPS'24☆30Updated 2 months ago
- This is the official code for NeurIPS 2023 paper "Learning Unseen Modality Interaction"☆16Updated last year
- ☆62Updated 4 months ago
- ☆12Updated 2 years ago
- offical implementation of "Calibrating Multimodal Learning" on ICML 2023☆20Updated 2 years ago
- Characterizing and overcoming the greedy nature of learning in multi-modal deep neural networks☆30Updated 3 years ago
- [ICLR 23 oral] The Modality Focusing Hypothesis: Towards Understanding Crossmodal Knowledge Distillation☆46Updated 2 years ago
- [CVPR 2024] FairCLIP: Harnessing Fairness in Vision-Language Learning☆96Updated 4 months ago
- Symile is a flexible, architecture-agnostic contrastive loss that enables training modality-specific representations for any number of mo…