oneHuster / MixupE
Codes for "MixupE: Understanding and Improving Mixup from Directional Derivative Perspective" UAI 2023 Oral
☆28Updated last year
Related projects ⓘ
Alternatives and complementary repositories for MixupE
- Training-free data valuation on deep neural network applications. (ICML-2022)☆22Updated 2 years ago
- Discover and Cure: Concept-aware Mitigation of Spurious Correlation (ICML 2023)☆40Updated 7 months ago
- Efficient and Online Dataset Growth Algorithm (with cleanness and diversity awareness) to deal with growing web data☆19Updated 3 months ago
- Python library for data stream learning☆28Updated 2 months ago
- ☆81Updated last year
- [NeurIPS 2023] Code release for "Going Beyond Linear Mode Connectivity: The Layerwise Linear Feature Connectivity"☆17Updated last year
- Data Optimization in Deep Learning: A Survey☆16Updated last year
- ICLR 2024, Towards Lossless Dataset Distillation via Difficulty-Aligned Trajectory Matching☆94Updated 5 months ago
- AdaMerging: Adaptive Model Merging for Multi-Task Learning. ICLR, 2024.☆52Updated 3 weeks ago
- ICLR 2022 (Spolight): Continual Learning With Filter Atom Swapping☆14Updated last year
- Deep Learning & Information Bottleneck☆50Updated last year
- Towards understanding modern generative data augmentation techniques.☆24Updated last year
- ☆15Updated 9 months ago
- ☆31Updated last year
- Revisiting Efficient Training Algorithms For Transformer-based Language Models (NeurIPS 2023)☆79Updated last year
- [EMNLP 2023 Main] Sparse Low-rank Adaptation of Pre-trained Language Models☆70Updated 8 months ago
- [ICLR 2024] Improving Convergence and Generalization Using Parameter Symmetries☆28Updated 5 months ago
- Welcome to the 'In Context Learning Theory' Reading Group☆22Updated 2 weeks ago
- Code for paper: “What Data Benefits My Classifier?” Enhancing Model Performance and Interpretability through Influence-Based Data Selecti…☆22Updated 6 months ago
- [NeurIPS'24 Oral] HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning☆76Updated this week
- `dattri` is a PyTorch library for developing, benchmarking, and deploying efficient data attribution algorithms.☆33Updated 3 weeks ago
- ☆16Updated last year
- Implementaiton of "DiLM: Distilling Dataset into Language Model for Text-level Dataset Distillation" (accepted by NAACL2024 Findings)".☆14Updated 2 weeks ago
- Efficient Dataset Distillation by Representative Matching☆107Updated 8 months ago
- [CVPR 2024] On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigm☆52Updated 6 months ago
- This is the official implementation for the paper: Use Your INSTINCT: INSTruction optimization usIng Neural bandits Coupled with Transfor…☆36Updated 5 months ago
- Awesome Learn From Model Beyond Fine-Tuning: A Survey☆50Updated 11 months ago
- [NeurIPS 2024] BLoB: Bayesian Low-Rank Adaptation by Backpropagation for Large Language Models☆21Updated this week
- ☆15Updated last week
- ZhiJian: A Unifying and Rapidly Deployable Toolbox for Pre-trained Model Reuse☆51Updated last year