{"total":17,"rows":[{"id":"2309.15698","title":"Deep Model Fusion: A Survey","created":"2023-09-27","cited_by_count":91,"area":null},{"id":"2111.12229","title":"Subspace Adversarial Training","created":"2021-11-24","cited_by_count":41,"area":null},{"id":"2405.16002","title":"Does SGD really happen in tiny subspaces?","created":"2024-05-25","cited_by_count":36,"area":null},{"id":"2305.17446","title":"Fine-tuning Happens in Tiny Subspaces: Exploring Intrinsic Task-specific Subspaces of Pre-trained Language Models","created":"2023-05-27","cited_by_count":19,"area":null},{"id":"2305.01134","title":"PGrad: Learning Principal Gradients For Domain Generalization","created":"2023-05-02","cited_by_count":8,"area":null},{"id":"2103.11154","title":"Low Dimensional Landscape Hypothesis is True: DNNs can be Trained in Tiny Subspaces","created":"2021-03-20","cited_by_count":5,"area":null},{"id":"2312.13247","title":"Enhancing Neural Training via a Correlated Dynamics Model","created":"2023-12-20","cited_by_count":5,"area":null},{"id":"2409.16722","title":"PMSS: Pretrained Matrices Skeleton Selection for LLM Fine-tuning","created":"2024-09-25","cited_by_count":5,"area":null},{"id":"2507.08091","title":"Low-rank Momentum Factorization for Memory Efficient Training","created":"2025-07-10","cited_by_count":4,"area":null},{"id":"2211.05554","title":"Robust Federated Learning against both Data Heterogeneity and Poisoning Attack via Aggregation Optimization","created":"2022-11-10","cited_by_count":3,"area":null},{"id":"2407.03641","title":"Learning Scalable Model Soup on a Single GPU: An Efficient Subspace Training Strategy","created":"2024-07-04","cited_by_count":3,"area":null},{"id":"2407.10237","title":"Towards Green AI: Current status and future research","created":"2024-05-01","cited_by_count":2,"area":null},{"id":"2411.06770","title":"Sketched Adaptive Federated Deep Learning: A Sharp Convergence Analysis","created":"2024-11-11","cited_by_count":1,"area":null},{"id":"2505.18107","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2203.15297","title":"Kernel Modulation: A Parameter-Efficient Method for Training Convolutional Neural Networks","created":"2022-03-29","cited_by_count":0,"area":null},{"id":"2412.13928","title":"Subspace Langevin Monte Carlo","created":"2024-12-18","cited_by_count":0,"area":null},{"id":"2609.14339","title":"Communication-Efficient LLM Adaptation over Decentralized GPU Meshes","created":"2026-09-13","cited_by_count":0,"area":null}],"next_cursor":null}