Cranial-XIX / FAMO
Official PyTorch Implementation for Fast Adaptive Multitask Optimization (FAMO)
☆71Updated 6 months ago
Related projects ⓘ
Alternatives and complementary repositories for FAMO
- Official PyTorch Implementation for Conflict-Averse Gradient Descent (CAGrad)☆112Updated last year
- The Implementation of "Auto-Lambda: Disentangling Dynamic Task Relationships" [TMLR 2022].☆129Updated last year
- Paper List for Multi-Task Learning (focus on architectures and optimization for MTL)☆40Updated 11 months ago
- ☆47Updated 2 years ago
- Official implementation of "Multi-Task Learning as a Bargaining Game" [ICML 2022]☆207Updated 6 months ago
- ☆40Updated last year
- ☆74Updated last year
- AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning☆112Updated 3 years ago
- Code for ICML2023 paper, DDGR: Continual Learning with Deep Diffusion-based Generative Replay.☆30Updated last year
- Code release of paper "ForkMerge: Mitigating Negative Transfer in Auxiliary-Task Learning" (NeurIPS 2023)☆14Updated 10 months ago
- Collection of papers and resources for data augmentation (DA) in visual reinforcement learning (RL).☆71Updated 7 months ago
- [ICLR 2022] code for "Towards building a group-based unsupervised representation disentanglement framework"☆15Updated 2 years ago
- Code release for "Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning" (NeurIPS 2023), https://ar…☆55Updated last month
- Model Zoos for Continual Learning (ICLR 22)☆41Updated last year
- Crawl & Visualize ICLR 2023 Data from OpenReview☆74Updated last year
- ☆52Updated last week
- [ACL 2023] Code for paper “Tailoring Instructions to Student’s Learning Levels Boosts Knowledge Distillation”(https://arxiv.org/abs/2305.…☆37Updated last year
- Metrics for "Beyond neural scaling laws: beating power law scaling via data pruning " (NeurIPS 2022 Outstanding Paper Award)☆53Updated last year
- ☆22Updated 2 years ago
- Code release for Deep Incubation (https://arxiv.org/abs/2212.04129)☆91Updated last year
- Official implementation for Equivariant Architectures for Learning in Deep Weight Spaces [ICML 2023]☆83Updated last year
- Official Pytorch's implementation of RotoGrad☆73Updated last year
- ☆31Updated 3 weeks ago
- A paper list of world model☆25Updated 6 months ago
- ICLR2023 statistics☆60Updated last year
- Mixture of Attention Heads☆39Updated 2 years ago
- OpenReivew Submission Visualization (ICLR 2024/2025)☆142Updated last month
- Official Code for NeurIPS 2022 Paper: How Mask Matters: Towards Theoretical Understandings of Masked Autoencoders☆55Updated last year
- Thisi is the official code base for paper "Think Before You Act: Decision Transformers with Internal Working Memory"☆19Updated 4 months ago
- Code for "Optimizing DDPM Sampling with Shortcut Fine-Tuning" (https://arxiv.org/abs/2301.13362), ICML 2023☆24Updated last year