Cranial-XIX / FAMOLinks
Official PyTorch Implementation for Fast Adaptive Multitask Optimization (FAMO)
☆90Updated last year
Alternatives and similar repositories for FAMO
Users that are interested in FAMO are comparing it to the libraries listed below
Sorting:
- Official implementation of "Multi-Task Learning as a Bargaining Game" [ICML 2022]☆225Updated last year
- Official PyTorch Implementation for Conflict-Averse Gradient Descent (CAGrad)☆124Updated last year
- Paper List for Multi-Task Learning (focus on architectures and optimization for MTL)☆47Updated last year
- The Implementation of "Auto-Lambda: Disentangling Dynamic Task Relationships" [TMLR 2022].☆135Updated 2 years ago
- ICLR2023 statistics☆60Updated last year
- ☆46Updated 2 years ago
- ☆45Updated 2 years ago
- Code release of paper "ForkMerge: Mitigating Negative Transfer in Auxiliary-Task Learning" (NeurIPS 2023)☆17Updated last year
- Some thoughts about writing scientific papers☆19Updated 7 months ago
- ☆32Updated 8 months ago
- [ICLR 2024] Improving Convergence and Generalization Using Parameter Symmetries☆29Updated last year
- Crawl & Visualize ICLR 2023 Data from OpenReview☆84Updated 2 years ago
- Official repo for PAC-Bayes Information Bottleneck. ICLR 2022.☆49Updated 3 years ago
- ICLR 2023 Paper submission analysis from https://openreview.net/group?id=ICLR.cc/2023/Conference☆105Updated 2 years ago
- Collection of papers and resources for data augmentation (DA) in visual reinforcement learning (RL).☆77Updated last year
- ☆12Updated 2 years ago
- Benchmark for Natural Temporal Distribution Shift (NeurIPS 2022)☆66Updated 2 years ago
- [ICLR 2023 (Spotlight)] Domain-Indexing Variational Bayes: Interpretable Domain Index for Domain Adaptation☆38Updated last year
- A python package providing a benchmark with various specified distribution shift patterns.☆58Updated last year
- [ICLR 24 Oral/Outstanding Paper Honorable Mention Award 🎉]☆36Updated last year
- Code repo for the NeurIPS 2021 paper "Online Adaption to Label Distribution Shift".☆15Updated 2 years ago
- Code for "Surgical Fine-Tuning Improves Adaptation to Distribution Shifts" published at ICLR 2023☆28Updated 2 years ago
- [NeurIPS21] TTT++: When Does Self-supervised Test-time Training Fail or Thrive?☆70Updated 3 years ago
- AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning☆112Updated 4 years ago
- Metrics for "Beyond neural scaling laws: beating power law scaling via data pruning " (NeurIPS 2022 Outstanding Paper Award)☆56Updated 2 years ago
- ☆63Updated 3 years ago
- ☆73Updated 9 months ago
- [NeurIPS2023] Official code of "Understanding Contrastive Learning via Distributionally Robust Optimization"☆40Updated last year
- [ICLR 2023, ICLR DG oral] PAIR, the optimizer and model selection criteria for OOD Generalization☆53Updated last year
- ☆17Updated 2 years ago