{"list":"other","total":60,"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"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":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"2111.09543","title":"DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing","created":"2021-11-18","cited_by_count":1254},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"1708.06733","title":"BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain","created":"2017-08-22","cited_by_count":1106},{"id":"1712.05526","title":"Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning","created":"2017-12-15","cited_by_count":1055},{"id":"1802.01548","title":"Regularized Evolution for Image Classifier Architecture Search","created":"2018-02-05","cited_by_count":909},{"id":"2306.01708","title":"TIES-Merging: Resolving Interference When Merging Models","created":"2023-06-02","cited_by_count":818},{"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":"2202.09368","title":"Mixture-of-Experts with Expert Choice Routing","created":"2022-02-18","cited_by_count":623},{"id":"2111.09832","title":"Merging Models with Fisher-Weighted Averaging","created":"2021-11-18","cited_by_count":621},{"id":"1805.12185","title":"Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks","created":"2018-05-30","cited_by_count":580},{"id":"2004.06660","title":"Weight Poisoning Attacks on Pre-trained Models","created":"2020-04-14","cited_by_count":341},{"id":"2006.03677","title":"Visual Transformers: Token-based Image Representation and Processing for Computer Vision","created":"2020-06-05","cited_by_count":334},{"id":"2011.10369","title":"ONION: A Simple and Effective Defense Against Textual Backdoor Attacks","created":"2020-11-20","cited_by_count":263},{"id":"2110.11571","title":"Anti-Backdoor Learning: Training Clean Models on Poisoned Data","created":"2021-10-22","cited_by_count":263},{"id":"2110.14430","title":"Adversarial Neuron Pruning Purifies Backdoored Deep Models","created":"2021-10-27","cited_by_count":235},{"id":"1905.12457","title":"A backdoor attack against LSTM-based text classification systems","created":"2019-05-29","cited_by_count":227},{"id":"2105.12400","title":"Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger","created":"2021-05-26","cited_by_count":222},{"id":"1901.11117","title":"The Evolved Transformer","created":"2019-01-30","cited_by_count":180},{"id":"2110.03735","title":"Adversarial Unlearning of Backdoors via Implicit Hypergradient","created":"2021-10-07","cited_by_count":166},{"id":"2109.14545","title":"Activation Functions in Deep Learning: A Comprehensive Survey and Benchmark","created":"2021-09-29","cited_by_count":155},{"id":"2301.08727","title":"Neural Architecture Search: Insights from 1000 Papers","created":"2023-01-20","cited_by_count":139},{"id":"1902.11175","title":"One-Shot Federated Learning","created":"2019-02-28","cited_by_count":125},{"id":"2007.15802","title":"Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Cases","created":"2020-07-31","cited_by_count":95},{"id":"2104.08646","title":"Competency Problems: On Finding and Removing Artifacts in Language Data","created":"2021-04-17","cited_by_count":91},{"id":"2106.06361","title":"Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution","created":"2021-06-11","cited_by_count":89},{"id":"2104.02361","title":"Backdoor Attack in the Physical World","created":"2021-04-06","cited_by_count":84},{"id":"1812.03128","title":"Backdooring Convolutional Neural Networks via Targeted Weight Perturbations","created":"2018-12-07","cited_by_count":69},{"id":"2305.14876","title":"Reconstructive Neuron Pruning for Backdoor Defense","created":"2023-05-24","cited_by_count":59},{"id":"2210.09545","title":"Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models","created":"2022-10-18","cited_by_count":57},{"id":"2205.06900","title":"MM-BD: Post-Training Detection of Backdoor Attacks with Arbitrary Backdoor Pattern Types Using a Maximum Margin Statistic","created":"2022-05-13","cited_by_count":55},{"id":"2304.02786","title":"UNICORN: A Unified Backdoor Trigger Inversion Framework","created":"2023-04-05","cited_by_count":46},{"id":"2405.09786","title":"IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling Consistency","created":"2024-05-16","cited_by_count":39},{"id":"2310.01875","title":"Towards Stable Backdoor Purification through Feature Shift Tuning","created":"2023-10-03","cited_by_count":32},{"id":"2402.15070","title":"Enhancing One-Shot Federated Learning Through Data and Ensemble Co-Boosting","created":"2024-02-23","cited_by_count":27},{"id":"2302.01762","title":"BackdoorBox: A Python Toolbox for Backdoor Learning","created":"2023-02-01","cited_by_count":26},{"id":"2402.19334","title":"Here's a Free Lunch: Sanitizing Backdoored Models with Model Merge","created":"2024-02-29","cited_by_count":26},{"id":"2406.12257","title":"CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models","created":"2024-06-18","cited_by_count":24},{"id":"2305.11596","title":"Mitigating Backdoor Poisoning Attacks through the Lens of Spurious Correlation","created":"2023-05-19","cited_by_count":21},{"id":"2405.11227","title":"BadActs: A Universal Backdoor Defense in the Activation Space","created":"2024-05-18","cited_by_count":21},{"id":"2401.15295","title":"Shortcuts Everywhere and Nowhere: Exploring Multi-Trigger Backdoor Attacks","created":"2024-01-27","cited_by_count":19},{"id":"2404.19597","title":"TuBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning","created":"2024-04-30","cited_by_count":14},{"id":"2410.13910","title":"Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace","created":"2024-10-17","cited_by_count":14},{"id":"2308.03906","title":"TIJO: Trigger Inversion with Joint Optimization for Defending Multimodal Backdoored Models","created":"2023-08-07","cited_by_count":12},{"id":"2211.01806","title":"BATT: Backdoor Attack with Transformation-based Triggers","created":"2022-11-02","cited_by_count":11},{"id":"2308.12439","title":"BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection","created":"2023-08-23","cited_by_count":11},{"id":"2411.09263","title":"Rethinking Weight-Averaged Model-merging","created":"2024-11-14","cited_by_count":8},{"id":"2302.14500","title":"FreeEagle: Detecting Complex Neural Trojans in Data-Free Cases","created":"2023-02-28","cited_by_count":7},{"id":"2411.18280","title":"Neutralizing Backdoors through Information Conflicts for Large Language Models","created":"2024-11-27","cited_by_count":5},{"id":"2402.17465","title":"Model X-ray:Detecting Backdoored Models via Decision Boundary","created":"2024-02-27","cited_by_count":3},{"id":"2405.11575","title":"SEEP: Training Dynamics Grounds Latent Representation Search for Mitigating Backdoor Poisoning Attacks","created":"2024-05-19","cited_by_count":3},{"id":"2407.11372","title":"UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening","created":"2024-07-16","cited_by_count":2}],"next_cursor":null}