{"list":"other","total":82,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"1506.06724","title":"Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books","created":"2015-06-22","cited_by_count":1043},{"id":"2209.10652","title":"Toy Models of Superposition","created":"2022-09-21","cited_by_count":971},{"id":"1909.00512","title":"How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings","created":"2019-09-02","cited_by_count":784},{"id":"2008.08186","title":"Prevalence of Neural Collapse during the terminal phase of deep learning training","created":"2020-08-18","cited_by_count":719},{"id":"2305.07759","title":"TinyStories: How Small Can Language Models Be and Still Speak Coherent English?","created":"2023-05-12","cited_by_count":449},{"id":"2305.17493","title":"The Curse of Recursion: Training on Generated Data Makes Models Forget","created":"2023-05-27","cited_by_count":356},{"id":"2105.02375","title":"A Geometric Analysis of Neural Collapse with Unconstrained Features","created":"2021-05-06","cited_by_count":227},{"id":"2101.12699","title":"Exploring Deep Neural Networks via Layer-Peeled Model: Minority Collapse in Imbalanced Training","created":"2021-01-29","cited_by_count":166},{"id":"2106.02073","title":"Neural Collapse Under MSE Loss: Proximity to and Dynamics on the Central Path","created":"2021-06-03","cited_by_count":158},{"id":"1711.03953","title":"Breaking the Softmax Bottleneck: A High-Rank RNN Language Model","created":"2017-11-10","cited_by_count":152},{"id":"2404.01413","title":"Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Data","created":"2024-04-01","cited_by_count":151},{"id":"2011.11619","title":"Neural collapse with unconstrained features","created":"2020-11-23","cited_by_count":142},{"id":"2202.08087","title":"Extended Unconstrained Features Model for Exploring Deep Neural Collapse","created":"2022-02-16","cited_by_count":102},{"id":"2112.15121","title":"On the Role of Neural Collapse in Transfer Learning","created":"2021-12-30","cited_by_count":100},{"id":"2203.09081","title":"Inducing Neural Collapse in Imbalanced Learning: Do We Really Need a Learnable Classifier at the End of Deep Neural Network?","created":"2022-03-17","cited_by_count":100},{"id":"2206.04041","title":"Neural Collapse: A Review on Modelling Principles and Generalization","created":"2022-06-08","cited_by_count":95},{"id":"2008.11865","title":"Traces of Class/Cross-Class Structure Pervade Deep Learning Spectra","created":"2020-08-27","cited_by_count":94},{"id":"2403.15796","title":"Understanding Emergent Abilities of Language Models from the Loss Perspective","created":"2024-03-23","cited_by_count":94},{"id":"2208.05512","title":"Imbalance Trouble: Revisiting Neural-Collapse Geometry","created":"2022-08-10","cited_by_count":80},{"id":"2210.02192","title":"Are All Losses Created Equal: A Neural Collapse Perspective","created":"2022-10-04","cited_by_count":78},{"id":"2202.08384","title":"Limitations of Neural Collapse for Understanding Generalization in Deep Learning","created":"2022-02-17","cited_by_count":63},{"id":"2404.09937","title":"Compression Represents Intelligence Linearly","created":"2024-04-15","cited_by_count":56},{"id":"2303.10058","title":"No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifier","created":"2023-03-17","cited_by_count":55},{"id":"2002.09773","title":"Revealing the Structure of Deep Neural Networks via Convex Duality","created":"2020-02-22","cited_by_count":54},{"id":"2012.05420","title":"On the emergence of simplex symmetry in the final and penultimate layers of neural network classifiers","created":"2020-12-10","cited_by_count":52},{"id":"2012.08465","title":"Neural Collapse with Cross-Entropy Loss","created":"2020-12-15","cited_by_count":52},{"id":"2209.09211","title":"Neural Collapse with Normalized Features: A Geometric Analysis over the Riemannian Manifold","created":"2022-09-19","cited_by_count":50},{"id":"2301.01100","title":"Understanding Imbalanced Semantic Segmentation Through Neural Collapse","created":"2023-01-03","cited_by_count":46},{"id":"2305.13165","title":"Deep Neural Collapse Is Provably Optimal for the Deep Unconstrained Features Model","created":"2023-05-22","cited_by_count":43},{"id":"2310.06823","title":"NECO: NEural Collapse Based Out-of-distribution detection","created":"2023-10-10","cited_by_count":42},{"id":"2206.02768","title":"The Neural Covariance SDE: Shaped Infinite Depth-and-Width Networks at Initialization","created":"2022-06-06","cited_by_count":41},{"id":"2301.00437","title":"Neural Collapse in Deep Linear Networks: From Balanced to Imbalanced Data","created":"2023-01-01","cited_by_count":40},{"id":"2310.05351","title":"Generalized Neural Collapse for a Large Number of Classes","created":"2023-10-09","cited_by_count":39},{"id":"2309.09725","title":"Neural Collapse for Unconstrained Feature Model under Cross-entropy Loss with Imbalanced Data","created":"2023-09-18","cited_by_count":38},{"id":"2101.00072","title":"Explicit regularization and implicit bias in deep network classifiers trained with the square loss","created":"2020-12-31","cited_by_count":37},{"id":"2210.17020","title":"A Law of Data Separation in Deep Learning","created":"2022-10-31","cited_by_count":36},{"id":"2210.16658","title":"Perturbation Analysis of Neural Collapse","created":"2022-10-29","cited_by_count":35},{"id":"2305.19753","title":"The Tunnel Effect: Building Data Representations in Deep Neural Networks","created":"2023-05-31","cited_by_count":34},{"id":"2311.02960","title":"Understanding Deep Representation Learning via Layerwise Feature Compression and Discrimination","created":"2023-11-06","cited_by_count":32},{"id":"2012.10424","title":"Separation and Concentration in Deep Networks","created":"2020-12-18","cited_by_count":30},{"id":"2302.12453","title":"Inducing Neural Collapse in Deep Long-tailed Learning","created":"2023-02-24","cited_by_count":28},{"id":"2212.12206","title":"Understanding and Improving Transfer Learning of Deep Models via Neural Collapse","created":"2022-12-23","cited_by_count":24},{"id":"2209.08378","title":"Linking Neural Collapse and L2 Normalization with Improved Out-of-Distribution Detection in Deep Neural Networks","created":"2022-09-17","cited_by_count":23},{"id":"2402.13728","title":"Average gradient outer product as a mechanism for deep neural collapse","created":"2024-02-21","cited_by_count":22},{"id":"2103.01499","title":"Demystifying Batch Normalization in ReLU Networks: Equivalent Convex Optimization Models and Implicit Regularization","created":"2021-03-02","cited_by_count":21},{"id":"2308.02760","title":"Neural Collapse in the Intermediate Hidden Layers of Classification Neural Networks","created":"2023-08-05","cited_by_count":21},{"id":"2201.08924","title":"Nearest Class-Center Simplification through Intermediate Layers","created":"2022-01-21","cited_by_count":20},{"id":"2307.01951","title":"A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks","created":"2023-07-04","cited_by_count":19},{"id":"2305.16427","title":"Neural (Tangent Kernel) Collapse","created":"2023-05-25","cited_by_count":18},{"id":"2208.02789","title":"Feature selection with gradient descent on two-layer networks in low-rotation regimes","created":"2022-08-04","cited_by_count":14},{"id":"2303.06484","title":"Generalizing and Decoupling Neural Collapse via Hyperspherical Uniformity Gap","created":"2023-03-11","cited_by_count":14},{"id":"2308.01746","title":"Neural Collapse Terminus: A Unified Solution for Class Incremental Learning and Its Variants","created":"2023-08-03","cited_by_count":14},{"id":"2310.15903","title":"Neural Collapse in Multi-label Learning with Pick-all-label Loss","created":"2023-10-24","cited_by_count":14},{"id":"2303.05689","title":"Inducing Neural Collapse to a Fixed Hierarchy-Aware Frame for Reducing Mistake Severity","created":"2023-03-10","cited_by_count":13},{"id":"2310.03010","title":"Spectral alignment of stochastic gradient descent for high-dimensional classification tasks","created":"2023-10-04","cited_by_count":13},{"id":"2202.09028","title":"On the Implicit Bias Towards Minimal Depth of Deep Neural Networks","created":"2022-02-18","cited_by_count":12},{"id":"2405.00985","title":"Progressive Feedforward Collapse of ResNet Training","created":"2024-05-02","cited_by_count":12},{"id":"2402.03979","title":"Cross Entropy versus Label Smoothing: A Neural Collapse Perspective","created":"2024-02-06","cited_by_count":11},{"id":"2402.03991","title":"Provable Emergence of Deep Neural Collapse and Low-Rank Bias in $L^2$-Regularized Nonlinear Networks","created":"2024-02-06","cited_by_count":11},{"id":"2404.06106","title":"Unifying Low Dimensional Spectra in Deep Learning","created":"2024-04-09","cited_by_count":11},{"id":"2401.01710","title":"EPA: Neural Collapse Inspired Robust Out-of-Distribution Detector","created":"2024-01-03","cited_by_count":10},{"id":"2405.08920","title":"Neural Collapse Meets Differential Privacy: Curious Behaviors of NoisyGD with Near-perfect Representation Learning","created":"2024-05-14","cited_by_count":8},{"id":"2304.08914","title":"A Study of Neural Collapse Phenomenon: Grassmannian Frame, Symmetry and Generalization","created":"2023-04-18","cited_by_count":7},{"id":"2310.08358","title":"Towards Demystifying the Generalization Behaviors When Neural Collapse Emerges","created":"2023-10-12","cited_by_count":7},{"id":"2402.06171","title":"Pushing Boundaries: Mixup's Influence on Neural Collapse","created":"2024-02-09","cited_by_count":7},{"id":"2107.12547","title":"Probing neural networks with t-SNE, class-specific projections and a guided tour","created":"2021-07-27","cited_by_count":6},{"id":"2202.06467","title":"NeuroMixGDP: A Neural Collapse-Inspired Random Mixup for Private Data Release","created":"2022-02-14","cited_by_count":2},{"id":"2306.15955","title":"Understanding Prompt Tuning for V-L Models Through the Lens of Neural Collapse","created":"2023-06-28","cited_by_count":2},{"id":"2404.02719","title":"Can We Understand Plasticity Through Neural Collapse?","created":"2024-04-03","cited_by_count":2},{"id":"2310.00451","title":"On the Role of Neural Collapse in Meta Learning Models for Few-shot Learning","created":"2023-09-30","cited_by_count":1}],"next_cursor":null}