wjxts / RegularizedBN
☆20Updated last year
Related projects: ⓘ
- PyTorch implementation of "From Sparse to Soft Mixtures of Experts"☆38Updated last year
- The official repository for our paper "The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns …☆15Updated 10 months ago
- Structured Pruning Adapters in PyTorch☆15Updated last year
- [ICLR 2023] "Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers" by Tianlong Chen*, Zhenyu Zhang*, Ajay Jaiswal…☆42Updated last year
- [ICLR 2021] "Long Live the Lottery: The Existence of Winning Tickets in Lifelong Learning" by Tianlong Chen*, Zhenyu Zhang*, Sijia Liu, S…☆22Updated 2 years ago
- [NeurIPS2023] Make Your Pre-trained Model Reversible: From Parameter to Memory Efficient Fine-Tuning☆28Updated last year
- Official code for "pi-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation", ICML 2023.☆32Updated last year
- EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation and Modal-adaptive Pruning (ACL 2023)☆19Updated last year
- Representation Surgery for Multi-Task Model Merging. ICML, 2024.☆23Updated 2 weeks ago
- Mixture of Attention Heads☆36Updated last year
- ☆32Updated 3 years ago
- On the Effectiveness of Parameter-Efficient Fine-Tuning☆38Updated 10 months ago
- [ICCV23] Official implementation of eP-ALM: Efficient Perceptual Augmentation of Language Models.☆27Updated 10 months ago
- ☆28Updated last year
- Code for T-MARS data filtering☆34Updated last year
- HGRN2: Gated Linear RNNs with State Expansion☆46Updated 3 weeks ago
- [ACL 2023] Code for paper “Tailoring Instructions to Student’s Learning Levels Boosts Knowledge Distillation”(https://arxiv.org/abs/2305.…☆38Updated last year
- Code for the PAPA paper☆27Updated last year
- Why Do We Need Weight Decay in Modern Deep Learning? [arXiv, Oct 2023]☆41Updated 11 months ago
- Official repo of Progressive Data Expansion: data, code and evaluation☆26Updated 10 months ago
- Official Code for ICLR 2024 Paper: Non-negative Contrastive Learning☆36Updated 4 months ago
- [ICML 2024] Junk DNA Hypothesis: A Task-Centric Angle of LLM Pre-trained Weights through Sparsity; Lu Yin*, Ajay Jaiswal*, Shiwei Liu, So…☆14Updated 3 months ago
- ☆15Updated last year
- Weighted Training for Cross-Task Learning☆15Updated last year
- ☆16Updated last year
- ☆26Updated 2 years ago
- [EVA ICLR'23; LARA ICML'22] Efficient attention mechanisms via control variates, random features, and importance sampling☆78Updated last year
- (CVPR 2022) Automated Progressive Learning for Efficient Training of Vision Transformers☆24Updated 2 years ago
- Curse-of-memory phenomenon of RNNs in sequence modelling☆17Updated this week
- Metrics for "Beyond neural scaling laws: beating power law scaling via data pruning " (NeurIPS 2022 Outstanding Paper Award)☆51Updated last year