{"list":"other","total":57,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"id":"2208.12242","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","created":"2022-08-25","cited_by_count":3300},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"1610.05820","title":"Membership Inference Attacks against Machine Learning Models","created":"2016-10-18","cited_by_count":2281},{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","created":"2022-06-22","cited_by_count":1295},{"id":"2104.13478","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","created":"2021-04-27","cited_by_count":1167},{"id":"1602.07576","title":"Group Equivariant Convolutional Networks","created":"2016-02-24","cited_by_count":1165},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120},{"id":"2402.09353","title":"DoRA: Weight-Decomposed Low-Rank Adaptation","created":"2024-02-14","cited_by_count":758},{"id":"1802.08219","title":"Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds","created":"2018-02-22","cited_by_count":746},{"id":"2403.14608","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","created":"2024-03-21","cited_by_count":656},{"id":"2209.04836","title":"Git Re-Basin: Merging Models modulo Permutation Symmetries","created":"2022-09-11","cited_by_count":471},{"id":"2402.12354","title":"LoRA+: Efficient Low Rank Adaptation of Large Models","created":"2024-02-19","cited_by_count":377},{"id":"1812.09902","title":"Invariant and Equivariant Graph Networks","created":"2018-12-24","cited_by_count":346},{"id":"2110.06296","title":"The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks","created":"2021-10-12","cited_by_count":291},{"id":"2404.02948","title":"PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models","created":"2024-04-03","cited_by_count":269},{"id":"2402.07841","title":"Do Membership Inference Attacks Work on Large Language Models?","created":"2024-02-12","cited_by_count":195},{"id":"2104.09459","title":"A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups","created":"2021-04-19","cited_by_count":187},{"id":"2202.13013","title":"Sign and Basis Invariant Networks for Spectral Graph Representation Learning","created":"2022-02-25","cited_by_count":179},{"id":"1901.09342","title":"On the Universality of Invariant Networks","created":"2019-01-27","cited_by_count":152},{"id":"2206.07758","title":"Reconstructing Training Data from Trained Neural Networks","created":"2022-06-15","cited_by_count":133},{"id":"2212.10650","title":"KronA: Parameter Efficient Tuning with Kronecker Adapter","created":"2022-12-20","cited_by_count":133},{"id":"2106.06610","title":"Scalars are universal: Equivariant machine learning, structured like classical physics","created":"2021-06-11","cited_by_count":127},{"id":"2006.04780","title":"Lorentz Group Equivariant Neural Network for Particle Physics","created":"2020-06-08","cited_by_count":121},{"id":"2002.11448","title":"Predicting Neural Network Accuracy from Weights","created":"2020-02-26","cited_by_count":110},{"id":"2211.06489","title":"Equivariance with Learned Canonicalization Functions","created":"2022-11-11","cited_by_count":109},{"id":"2301.12780","title":"Equivariant Architectures for Learning in Deep Weight Spaces","created":"2023-01-30","cited_by_count":107},{"id":"2209.12892","title":"Learning to Learn with Generative Models of Neural Network Checkpoints","created":"2022-09-26","cited_by_count":86},{"id":"2302.14040","title":"Permutation Equivariant Neural Functionals","created":"2023-02-27","cited_by_count":70},{"id":"2406.16201","title":"Blind Baselines Beat Membership Inference Attacks for Foundation Models","created":"2024-06-23","cited_by_count":69},{"id":"2002.05688","title":"Classifying the classifier: dissecting the weight space of neural networks","created":"2020-02-13","cited_by_count":65},{"id":"2403.12143","title":"Graph Neural Networks for Learning Equivariant Representations of Neural Networks","created":"2024-03-18","cited_by_count":59},{"id":"2211.09760","title":"VeLO: Training Versatile Learned Optimizers by Scaling Up","created":"2022-11-17","cited_by_count":57},{"id":"2312.04501","title":"Graph Metanetworks for Processing Diverse Neural Architectures","created":"2023-12-07","cited_by_count":57},{"id":"2402.16077","title":"Equivariant Frames and the Impossibility of Continuous Canonicalization","created":"2024-02-25","cited_by_count":43},{"id":"2205.02956","title":"Low Dimensional Invariant Embeddings for Universal Geometric Learning","created":"2022-05-05","cited_by_count":38},{"id":"2406.09413","title":"Interpreting the Weight Space of Customized Diffusion Models","created":"2024-06-13","cited_by_count":36},{"id":"2310.13397","title":"Equivariant Deep Weight Space Alignment","created":"2023-10-20","cited_by_count":35},{"id":"2405.18378","title":"A Canonicalization Perspective on Invariant and Equivariant Learning","created":"2024-05-28","cited_by_count":27},{"id":"2402.05232","title":"Universal Neural Functionals","created":"2024-02-07","cited_by_count":26},{"id":"2402.04081","title":"Improved Generalization of Weight Space Networks via Augmentations","created":"2024-02-06","cited_by_count":24},{"id":"2406.10685","title":"Scale Equivariant Graph Metanetworks","created":"2024-06-15","cited_by_count":24},{"id":"2405.20231","title":"The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof","created":"2024-05-30","cited_by_count":21},{"id":"2212.08630","title":"Brauer's Group Equivariant Neural Networks","created":"2022-12-16","cited_by_count":17},{"id":"2409.11697","title":"Monomial Matrix Group Equivariant Neural Functional Networks","created":"2024-09-18","cited_by_count":17},{"id":"2209.14991","title":"Machine learning and invariant theory","created":"2022-09-29","cited_by_count":13},{"id":"2305.16625","title":"Set-based Neural Network Encoding Without Weight Tying","created":"2023-05-26","cited_by_count":9},{"id":"2406.19395","title":"Dataset Size Recovery from LoRA Weights","created":"2024-06-27","cited_by_count":7}],"next_cursor":null}