{"total":18,"rows":[{"id":"2203.09795","title":"Three things everyone should know about Vision Transformers","created":"2022-03-18","cited_by_count":90,"area":null},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"area":null},{"id":"2203.16708","title":"Task Adaptive Parameter Sharing for Multi-Task Learning","created":"2022-03-30","cited_by_count":42,"area":null},{"id":"2205.06784","title":"KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learning","created":"2022-05-13","cited_by_count":41,"area":null},{"id":"2308.09610","title":"On the Effectiveness of LayerNorm Tuning for Continual Learning in Vision Transformers","created":"2023-08-18","cited_by_count":14,"area":null},{"id":"2311.03873","title":"Mini but Mighty: Finetuning ViTs with Mini Adapters","created":"2023-11-07","cited_by_count":6,"area":null},{"id":"2103.13894","title":"Boosting Binary Masks for Multi-Domain Learning through Affine Transformations","created":"2021-03-25","cited_by_count":5,"area":null},{"id":"2304.02321","title":"Few-shot Semantic Image Synthesis with Class Affinity Transfer","created":"2023-04-05","cited_by_count":4,"area":null},{"id":"2107.05445","title":"Disentangling Transfer and Interference in Multi-Domain Learning","created":"2021-07-02","cited_by_count":3,"area":null},{"id":"2303.04105","title":"Your representations are in the network: composable and parallel adaptation for large scale models","created":"2023-03-07","cited_by_count":3,"area":null},{"id":"2212.04221","title":"An Empirical Study on Multi-Domain Robust Semantic Segmentation","created":"2022-12-08","cited_by_count":2,"area":null},{"id":"2210.08101","title":"Budget-Aware Pruning for Multi-Domain Learning","created":"2022-10-14","cited_by_count":1,"area":null},{"id":"2307.08528","title":"Multi-Domain Learning with Modulation Adapters","created":"2023-07-17","cited_by_count":1,"area":null},{"id":"2310.06124","title":"Parameter-efficient Multi-Task and Multi-Domain Learning using Factorized Tensor Networks","created":"2023-10-09","cited_by_count":1,"area":null},{"id":"2402.16848","title":"InterroGate: Learning to Share, Specialize, and Prune Representations for Multi-task Learning","created":"2024-02-26","cited_by_count":1,"area":null},{"id":"2203.10463","title":"Unidirectional Thin Adapter for Efficient Adaptation of Deep Neural Networks","created":"2022-03-20","cited_by_count":0,"area":null},{"id":"2309.11464","title":"Budget-Aware Pruning: Handling Multiple Domains with Less Parameters","created":"2023-09-20","cited_by_count":0,"area":null},{"id":"2502.11085","title":"On the Importance of Pretraining Data Alignment for Atomic Property Prediction","created":"2025-02-16","cited_by_count":0,"area":null}],"next_cursor":null}