{"total":1755,"rows":[{"id":"2210.02186","title":"TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis","created":"2022-10-05","cited_by_count":1058,"area":null},{"id":"2310.06625","title":"iTransformer: Inverted Transformers Are Effective for Time Series Forecasting","created":"2023-10-10","cited_by_count":931,"area":null},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797,"area":null},{"id":"2410.06940","title":"Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think","created":"2024-10-09","cited_by_count":703,"area":"diffusion"},{"id":"2108.08810","title":"Do Vision Transformers See Like Convolutional Neural Networks?","created":"2021-08-19","cited_by_count":675,"area":null},{"id":"2209.12152","title":"All are Worth Words: A ViT Backbone for Diffusion Models","created":"2022-09-25","cited_by_count":502,"area":"diffusion"},{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422,"area":"mechinterp"},{"id":"2405.07987","title":"The Platonic Representation Hypothesis","created":"2024-05-13","cited_by_count":382,"area":null},{"id":"2107.04734","title":"Layer-wise Analysis of a Self-supervised Speech Representation Model","created":"2021-07-10","cited_by_count":298,"area":null},{"id":"2402.19072","title":"TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables","created":"2024-02-29","cited_by_count":248,"area":null},{"id":"2106.05001","title":"No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data","created":"2021-06-09","cited_by_count":241,"area":null},{"id":"2106.07682","title":"Revisiting Model Stitching to Compare Neural Representations","created":"2021-06-14","cited_by_count":209,"area":null},{"id":"2209.15430","title":"Relative representations enable zero-shot latent space communication","created":"2022-09-30","cited_by_count":191,"area":null},{"id":"2106.05945","title":"Does Knowledge Distillation Really Work?","created":"2021-06-10","cited_by_count":190,"area":"distill"},{"id":"2208.05592","title":"Patching open-vocabulary models by interpolating weights","created":"2022-08-10","cited_by_count":190,"area":null},{"id":"2202.00622","title":"Datamodels: Predicting Predictions from Training Data","created":"2022-02-01","cited_by_count":189,"area":null},{"id":"2303.05118","title":"SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model","created":"2023-03-09","cited_by_count":180,"area":null},{"id":"2305.03053","title":"ZipIt! Merging Models from Different Tasks without Training","created":"2023-05-04","cited_by_count":179,"area":null},{"id":"2108.01390","title":"Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer","created":"2021-08-03","cited_by_count":177,"area":"inference"},{"id":"2509.04259","title":"RL's Razor: Why Online Reinforcement Learning Forgets Less","created":"2025-09-04","cited_by_count":176,"area":"lr"},{"id":"2112.13890","title":"SPViT: Enabling Faster Vision Transformers via Soft Token Pruning","created":"2021-12-27","cited_by_count":167,"area":"inference"},{"id":"2205.13218","title":"A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning","created":"2022-05-26","cited_by_count":154,"area":null},{"id":"2212.08013","title":"FlexiViT: One Model for All Patch Sizes","created":"2022-12-15","cited_by_count":152,"area":null},{"id":"2205.09739","title":"Diverse Weight Averaging for Out-of-Distribution Generalization","created":"2022-05-19","cited_by_count":148,"area":null},{"id":"2406.19384","title":"The Remarkable Robustness of LLMs: Stages of Inference?","created":"2024-06-27","cited_by_count":146,"area":null},{"id":"2302.03025","title":"A Toy Model of Universality: Reverse Engineering How Networks Learn Group Operations","created":"2023-02-06","cited_by_count":144,"area":"mechinterp"},{"id":"2310.13018","title":"Getting aligned on representational alignment","created":"2023-10-18","cited_by_count":143,"area":null},{"id":"2209.15162","title":"Linearly Mapping from Image to Text Space","created":"2022-09-30","cited_by_count":142,"area":null},{"id":"2305.06329","title":"Similarity of Neural Network Models: A Survey of Functional and Representational Measures","created":"2023-05-10","cited_by_count":131,"area":null},{"id":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129,"area":null},{"id":"2402.11187","title":"LaCo: Large Language Model Pruning via Layer Collapse","created":"2024-02-17","cited_by_count":126,"area":null},{"id":"2309.07311","title":"Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs","created":"2023-09-13","cited_by_count":124,"area":null},{"id":"2410.19735","title":"Model merging with SVD to tie the Knots","created":"2024-10-25","cited_by_count":122,"area":null},{"id":"2205.13543","title":"Revealing the Dark Secrets of Masked Image Modeling","created":"2022-05-26","cited_by_count":117,"area":null},{"id":"2410.16032","title":"TimeMixer++: A General Time Series Pattern Machine for Universal Predictive Analysis","created":"2024-10-21","cited_by_count":116,"area":null},{"id":"2302.00861","title":"SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling","created":"2023-02-02","cited_by_count":115,"area":null},{"id":"2110.14739","title":"Generalized Shape Metrics on Neural Representations","created":"2021-10-27","cited_by_count":112,"area":null},{"id":"2206.02574","title":"On the duality between contrastive and non-contrastive self-supervised learning","created":"2022-06-03","cited_by_count":108,"area":null},{"id":"2310.06110","title":"Grokking as the Transition from Lazy to Rich Training Dynamics","created":"2023-10-09","cited_by_count":108,"area":null},{"id":"2401.12181","title":"Universal Neurons in GPT2 Language Models","created":"2024-01-22","cited_by_count":102,"area":"mechinterp"},{"id":"2507.01467","title":"Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think","created":"2025-07-02","cited_by_count":102,"area":"diffusion"},{"id":"2110.06976","title":"Representational Continuity for Unsupervised Continual Learning","created":"2021-10-13","cited_by_count":95,"area":null},{"id":"2204.07154","title":"MiniViT: Compressing Vision Transformers with Weight Multiplexing","created":"2022-04-14","cited_by_count":88,"area":null},{"id":"2210.16156","title":"Reliability of CKA as a Similarity Measure in Deep Learning","created":"2022-10-28","cited_by_count":87,"area":null},{"id":"2307.12732","title":"CLIP-KD: An Empirical Study of CLIP Model Distillation","created":"2023-07-24","cited_by_count":87,"area":"distill"},{"id":"2402.16842","title":"Asymmetry in Low-Rank Adapters of Foundation Models","created":"2024-02-26","cited_by_count":86,"area":null},{"id":"2601.07372","title":"Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models","created":"2026-01-12","cited_by_count":86,"area":"moe"},{"id":"2205.09357","title":"Continual Pre-Training Mitigates Forgetting in Language and Vision","created":"2022-05-19","cited_by_count":83,"area":null},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"area":null},{"id":"2103.13517","title":"A Broad Study on the Transferability of Visual Representations with Contrastive Learning","created":"2021-03-24","cited_by_count":78,"area":null},{"id":"2110.14633","title":"Similarity and Matching of Neural Network Representations","created":"2021-10-27","cited_by_count":78,"area":null},{"id":"2202.00661","title":"When Do Flat Minima Optimizers Work?","created":"2022-02-01","cited_by_count":78,"area":null},{"id":"2210.17409","title":"Deep Model Reassembly","created":"2022-10-24","cited_by_count":78,"area":null},{"id":"2310.19444","title":"One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation","created":"2023-10-30","cited_by_count":78,"area":"distill"},{"id":"2203.13381","title":"Probing Representation Forgetting in Supervised and Unsupervised Continual Learning","created":"2022-03-24","cited_by_count":76,"area":null},{"id":"2211.01201","title":"Human alignment of neural network representations","created":"2022-11-02","cited_by_count":74,"area":null},{"id":"2105.14602","title":"On the geometry of generalization and memorization in deep neural networks","created":"2021-05-30","cited_by_count":73,"area":null},{"id":"2108.04974","title":"SoK: How Robust is Image Classification Deep Neural Network Watermarking? (Extended Version)","created":"2021-08-11","cited_by_count":69,"area":null},{"id":"2307.09218","title":"A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning","created":"2023-07-16","cited_by_count":69,"area":null},{"id":"2301.11578","title":"Learning to Unlearn: Instance-wise Unlearning for Pre-trained Classifiers","created":"2023-01-27","cited_by_count":67,"area":"safety"},{"id":"2201.00058","title":"Representation Topology Divergence: A Method for Comparing Neural Network Representations","created":"2021-12-31","cited_by_count":66,"area":null},{"id":"2101.11109","title":"First Align, then Predict: Understanding the Cross-Lingual Ability of Multilingual BERT","created":"2021-01-26","cited_by_count":65,"area":null},{"id":"2202.12938","title":"Assessing the State of Self-Supervised Human Activity Recognition using Wearables","created":"2022-02-22","cited_by_count":65,"area":null},{"id":"2205.14258","title":"On the Symmetries of Deep Learning Models and their Internal Representations","created":"2022-05-27","cited_by_count":64,"area":null},{"id":"2307.00162","title":"What Do Self-Supervised Speech Models Know About Words?","created":"2023-06-30","cited_by_count":64,"area":null},{"id":"2208.07463","title":"Conv-Adapter: Exploring Parameter Efficient Transfer Learning for ConvNets","created":"2022-08-15","cited_by_count":62,"area":null},{"id":"2203.01825","title":"What Makes Transfer Learning Work For Medical Images: Feature Reuse & Other Factors","created":"2022-03-02","cited_by_count":61,"area":null},{"id":"2602.11451","title":"LoopFormer: Elastic-Depth Looped Transformers for Latent Reasoning via Shortcut Modulation","created":"2026-02-11","cited_by_count":61,"area":"lr"},{"id":"2102.07650","title":"Learning Student-Friendly Teacher Networks for Knowledge Distillation","created":"2021-02-12","cited_by_count":60,"area":"distill"},{"id":"2308.04657","title":"Which Tokens to Use? Investigating Token Reduction in Vision Transformers","created":"2023-08-09","cited_by_count":60,"area":"inference"},{"id":"2502.20578","title":"Interpreting CLIP with Hierarchical Sparse Autoencoders","created":"2025-02-27","cited_by_count":60,"area":"mechinterp"},{"id":"2207.03337","title":"Factorizing Knowledge in Neural Networks","created":"2022-07-04","cited_by_count":59,"area":null},{"id":"2302.04863","title":"Knowledge is a Region in Weight Space for Fine-tuned Language Models","created":"2023-02-09","cited_by_count":58,"area":null},{"id":"2307.08702","title":"Diffusion Models Beat GANs on Image Classification","created":"2023-07-17","cited_by_count":58,"area":"diffusion"},{"id":"2303.13132","title":"Masked Image Training for Generalizable Deep Image Denoising","created":"2023-03-23","cited_by_count":57,"area":null},{"id":"2103.13841","title":"Universal Representation Learning from Multiple Domains for Few-shot Classification","created":"2021-03-25","cited_by_count":56,"area":null},{"id":"2205.13692","title":"FedAvg with Fine Tuning: Local Updates Lead to Representation Learning","created":"2022-05-27","cited_by_count":56,"area":null},{"id":"2304.01663","title":"On the Stability-Plasticity Dilemma of Class-Incremental Learning","created":"2023-04-04","cited_by_count":56,"area":null},{"id":"2405.15471","title":"Emergence of a High-Dimensional Abstraction Phase in Language Transformers","created":"2024-05-24","cited_by_count":56,"area":null},{"id":"2409.17858","title":"How Feature Learning Can Improve Neural Scaling Laws","created":"2024-09-26","cited_by_count":56,"area":null},{"id":"2212.08045","title":"CLIPPO: Image-and-Language Understanding from Pixels Only","created":"2022-12-15","cited_by_count":55,"area":null},{"id":"2505.12540","title":"Harnessing the Universal Geometry of Embeddings","created":"2025-05-18","cited_by_count":55,"area":null},{"id":"2407.09298","title":"Transformer Layers as Painters","created":"2024-07-12","cited_by_count":54,"area":null},{"id":"2311.00664","title":"Latent Space Translation via Semantic Alignment","created":"2023-11-01","cited_by_count":52,"area":null},{"id":"2401.06187","title":"Scissorhands: Scrub Data Influence via Connection Sensitivity in Networks","created":"2024-01-11","cited_by_count":52,"area":"safety"},{"id":"2407.15017","title":"Knowledge Mechanisms in Large Language Models: A Survey and Perspective","created":"2024-07-22","cited_by_count":51,"area":null},{"id":"2208.04164","title":"Understanding Masked Image Modeling via Learning Occlusion Invariant Feature","created":"2022-08-08","cited_by_count":50,"area":null},{"id":"2409.14623","title":"From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks","created":"2024-09-22","cited_by_count":49,"area":null},{"id":"2103.04514","title":"Nondeterminism and Instability in Neural Network Optimization","created":"2021-03-08","cited_by_count":48,"area":null},{"id":"2205.15308","title":"Parameter-Efficient and Student-Friendly Knowledge Distillation","created":"2022-05-28","cited_by_count":47,"area":"distill"},{"id":"2104.00887","title":"Multiple Heads are Better than One: Few-shot Font Generation with Multiple Localized Experts","created":"2021-04-02","cited_by_count":46,"area":null},{"id":"2211.08110","title":"HeatViT: Hardware-Efficient Adaptive Token Pruning for Vision Transformers","created":"2022-11-15","cited_by_count":46,"area":"inference"},{"id":"2306.09346","title":"Rosetta Neurons: Mining the Common Units in a Model Zoo","created":"2023-06-15","cited_by_count":46,"area":null},{"id":"2210.04524","title":"Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigation","created":"2022-10-10","cited_by_count":45,"area":null},{"id":"2212.03862","title":"Teaching Matters: Investigating the Role of Supervision in Vision Transformers","created":"2022-12-07","cited_by_count":45,"area":null},{"id":"2206.00388","title":"Transfer without Forgetting","created":"2022-06-01","cited_by_count":44,"area":null},{"id":"2401.05224","title":"Do Vision and Language Encoders Represent the World Similarly?","created":"2024-01-10","cited_by_count":44,"area":null},{"id":"2602.14486","title":"Revisiting the Platonic Representation Hypothesis: An Aristotelian View","created":"2026-02-16","cited_by_count":44,"area":null},{"id":"2211.09703","title":"EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbones","created":"2022-11-17","cited_by_count":43,"area":null},{"id":"2501.19361","title":"We're Different, We're the Same: Creative Homogeneity Across LLMs","created":"2025-01-31","cited_by_count":42,"area":null}],"next_cursor":"100"}