{"list":"other","total":94,"rows":[{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"1610.05820","title":"Membership Inference Attacks against Machine Learning Models","created":"2016-10-18","cited_by_count":2281},{"id":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420},{"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":"1609.04836","title":"On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima","created":"2016-09-15","cited_by_count":1352},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"1712.09913","title":"Visualizing the Loss Landscape of Neural Nets","created":"2017-12-28","cited_by_count":1130},{"id":"2406.11717","title":"Refusal in Language Models Is Mediated by a Single Direction","created":"2024-06-17","cited_by_count":1032},{"id":"2210.07229","title":"Mass-Editing Memory in a Transformer","created":"2022-10-13","cited_by_count":1001},{"id":"1602.02697","title":"Practical Black-Box Attacks against Machine Learning","created":"2016-02-08","cited_by_count":903},{"id":"2205.05638","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","created":"2022-05-11","cited_by_count":896},{"id":"2306.01708","title":"TIES-Merging: Resolving Interference When Merging Models","created":"2023-06-02","cited_by_count":818},{"id":"1503.05671","title":"Optimizing Neural Networks with Kronecker-factored Approximate Curvature","created":"2015-03-19","cited_by_count":796},{"id":"2402.09353","title":"DoRA: Weight-Decomposed Low-Rank Adaptation","created":"2024-02-14","cited_by_count":758},{"id":"2311.03099","title":"Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch","created":"2023-11-06","cited_by_count":694},{"id":"2012.13255","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","created":"2020-12-22","cited_by_count":671},{"id":"1912.05671","title":"Linear Mode Connectivity and the Lottery Ticket Hypothesis","created":"2019-12-11","cited_by_count":637},{"id":"2111.09832","title":"Merging Models with Fisher-Weighted Averaging","created":"2021-11-18","cited_by_count":621},{"id":"1802.10026","title":"Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs","created":"2018-02-27","cited_by_count":588},{"id":"2002.06440","title":"Federated Learning with Matched Averaging","created":"2020-02-15","cited_by_count":564},{"id":"1703.11008","title":"Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data","created":"2017-03-31","cited_by_count":533},{"id":"2006.05929","title":"Dataset Condensation with Gradient Matching","created":"2020-06-10","cited_by_count":516},{"id":"2006.05467","title":"Pruning neural networks without any data by iteratively conserving synaptic flow","created":"2020-06-09","cited_by_count":479},{"id":"2209.04836","title":"Git Re-Basin: Merging Models modulo Permutation Symmetries","created":"2022-09-11","cited_by_count":471},{"id":"1912.02757","title":"Deep Ensembles: A Loss Landscape Perspective","created":"2019-12-05","cited_by_count":443},{"id":"2103.00065","title":"Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability","created":"2021-02-26","cited_by_count":427},{"id":"2408.05147","title":"Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2","created":"2024-08-09","cited_by_count":394},{"id":"1905.12022","title":"Bayesian Nonparametric Federated Learning of Neural Networks","created":"2019-05-28","cited_by_count":387},{"id":"2212.09849","title":"Dataless Knowledge Fusion by Merging Weights of Language Models","created":"2022-12-19","cited_by_count":387},{"id":"2402.12354","title":"LoRA+: Efficient Low Rank Adaptation of Large Models","created":"2024-02-19","cited_by_count":377},{"id":"1907.09693","title":"A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection","created":"2019-07-23","cited_by_count":374},{"id":"1804.08838","title":"Measuring the Intrinsic Dimension of Objective Landscapes","created":"2018-04-24","cited_by_count":370},{"id":"1611.01838","title":"Entropy-SGD: Biasing Gradient Descent Into Wide Valleys","created":"2016-11-06","cited_by_count":359},{"id":"2303.15361","title":"A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts","created":"2023-03-27","cited_by_count":359},{"id":"1704.00109","title":"Snapshot Ensembles: Train 1, get M for free","created":"2017-04-01","cited_by_count":350},{"id":"1803.00885","title":"Essentially No Barriers in Neural Network Energy Landscape","created":"2018-03-02","cited_by_count":330},{"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":"2408.07666","title":"Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities","created":"2024-08-14","cited_by_count":254},{"id":"1902.04742","title":"Uniform convergence may be unable to explain generalization in deep learning","created":"2019-02-13","cited_by_count":224},{"id":"1910.05653","title":"Model Fusion via Optimal Transport","created":"2019-10-12","cited_by_count":219},{"id":"2303.02536","title":"Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations","created":"2023-03-05","cited_by_count":209},{"id":"2403.13187","title":"Evolutionary Optimization of Model Merging Recipes","created":"2024-03-19","cited_by_count":208},{"id":"2404.03592","title":"ReFT: Representation Finetuning for Language Models","created":"2024-04-04","cited_by_count":197},{"id":"2004.12265","title":"Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias","created":"2020-04-26","cited_by_count":191},{"id":"2208.05592","title":"Patching open-vocabulary models by interpolating weights","created":"2022-08-10","cited_by_count":190},{"id":"2010.15110","title":"Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel","created":"2020-10-28","cited_by_count":187},{"id":"2305.03053","title":"ZipIt! Merging Models from Different Tasks without Training","created":"2023-05-04","cited_by_count":179},{"id":"2209.15594","title":"Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability","created":"2022-09-30","cited_by_count":155},{"id":"1602.01407","title":"A Kronecker-factored approximate Fisher matrix for convolution layers","created":"2016-02-03","cited_by_count":141},{"id":"2312.06795","title":"Model Breadcrumbs: Scaling Multi-Task Model Merging with Sparse Masks","created":"2023-12-11","cited_by_count":133},{"id":"2005.00060","title":"Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness","created":"2020-04-30","cited_by_count":132},{"id":"2105.12221","title":"Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances","created":"2021-05-25","cited_by_count":127},{"id":"2211.08403","title":"REPAIR: REnormalizing Permuted Activations for Interpolation Repair","created":"2022-11-15","cited_by_count":120},{"id":"2010.11635","title":"Continual Learning in Low-rank Orthogonal Subspaces","created":"2020-10-22","cited_by_count":99},{"id":"2102.10472","title":"Learning Neural Network Subspaces","created":"2021-02-20","cited_by_count":82},{"id":"2406.00034","title":"Adaptive Activation Steering: A Tuning-Free LLM Truthfulness Improvement Method for Diverse Hallucinations Categories","created":"2024-05-26","cited_by_count":77},{"id":"2102.13042","title":"Loss Surface Simplexes for Mode Connecting Volumes and Fast Ensembling","created":"2021-02-25","cited_by_count":75},{"id":"2310.04742","title":"Parameter Efficient Multi-task Model Fusion with Partial Linearization","created":"2023-10-07","cited_by_count":65},{"id":"1809.04790","title":"Adversarial Examples: Opportunities and Challenges","created":"2018-09-13","cited_by_count":63},{"id":"1907.02911","title":"Weight-space symmetry in deep networks gives rise to permutation saddles, connected by equal-loss valleys across the loss landscape","created":"2019-07-05","cited_by_count":63},{"id":"2302.04863","title":"Knowledge is a Region in Weight Space for Fine-tuned Language Models","created":"2023-02-09","cited_by_count":58},{"id":"1906.00586","title":"Discovering Neural Wirings","created":"2019-06-03","cited_by_count":56},{"id":"2408.07057","title":"A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning","created":"2024-08-13","cited_by_count":52},{"id":"2307.08286","title":"Going Beyond Linear Mode Connectivity: The Layerwise Linear Feature Connectivity","created":"2023-07-17","cited_by_count":50},{"id":"2309.10312","title":"Rigorously Assessing Natural Language Explanations of Neurons","created":"2023-09-19","cited_by_count":45},{"id":"2204.11326","title":"Beyond the Quadratic Approximation: the Multiscale Structure of Neural Network Loss Landscapes","created":"2022-04-24","cited_by_count":43},{"id":"2405.03097","title":"To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models","created":"2024-05-06","cited_by_count":43},{"id":"2404.05567","title":"Dense Training, Sparse Inference: Rethinking Training of Mixture-of-Experts Language Models","created":"2024-04-08","cited_by_count":42},{"id":"1907.10732","title":"Hessian based analysis of SGD for Deep Nets: Dynamics and Generalization","created":"2019-07-24","cited_by_count":37},{"id":"1912.01667","title":"A Survey of Black-Box Adversarial Attacks on Computer Vision Models","created":"2019-12-03","cited_by_count":37},{"id":"2207.06569","title":"Benign, Tempered, or Catastrophic: A Taxonomy of Overfitting","created":"2022-07-14","cited_by_count":36},{"id":"2310.05719","title":"Transformer Fusion with Optimal Transport","created":"2023-10-09","cited_by_count":36},{"id":"2402.18913","title":"AdaMergeX: Cross-Lingual Transfer with Large Language Models via Adaptive Adapter Merging","created":"2024-02-29","cited_by_count":34},{"id":"2409.04478","title":"Evaluating Open-Source Sparse Autoencoders on Disentangling Factual Knowledge in GPT-2 Small","created":"2024-09-05","cited_by_count":34},{"id":"2402.03660","title":"On the Emergence of Cross-Task Linearity in the Pretraining-Finetuning Paradigm","created":"2024-02-06","cited_by_count":26},{"id":"2306.16788","title":"Sparse Model Soups: A Recipe for Improved Pruning via Model Averaging","created":"2023-06-29","cited_by_count":20},{"id":"2406.11780","title":"Split, Unlearn, Merge: Leveraging Data Attributes for More Effective Unlearning in LLMs","created":"2024-06-17","cited_by_count":18},{"id":"2310.03010","title":"Spectral alignment of stochastic gradient descent for high-dimensional classification tasks","created":"2023-10-04","cited_by_count":13},{"id":"2405.10927","title":"Using Degeneracy in the Loss Landscape for Mechanistic Interpretability","created":"2024-05-17","cited_by_count":13},{"id":"1907.09061","title":"Understanding Adversarial Robustness Through Loss Landscape Geometries","created":"2019-07-22","cited_by_count":12},{"id":"2402.04051","title":"Analysis of Linear Mode Connectivity via Permutation-Based Weight Matching: With Insights into Other Permutation Search Methods","created":"2024-02-06","cited_by_count":9},{"id":"2404.10464","title":"DESTEIN: Navigating Detoxification of Language Models via Universal Steering Pairs and Head-wise Activation Fusion","created":"2024-04-16","cited_by_count":9},{"id":"2402.01342","title":"Improving Model Fusion by Training-time Neuron Alignment with Fixed Neuron Anchors","created":"2024-02-02","cited_by_count":7},{"id":"2305.14852","title":"Sparse Weight Averaging with Multiple Particles for Iterative Magnitude Pruning","created":"2023-05-24","cited_by_count":2},{"id":"2310.08681","title":"Fed-Safe: Securing Federated Learning in Healthcare Against Adversarial Attacks","created":"2023-10-12","cited_by_count":1}],"next_cursor":null}