{"list":"other","total":53,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"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":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120},{"id":"1708.06733","title":"BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain","created":"2017-08-22","cited_by_count":1106},{"id":"2306.01708","title":"TIES-Merging: Resolving Interference When Merging Models","created":"2023-06-02","cited_by_count":818},{"id":"1703.00121","title":"Remote Sensing Image Scene Classification: Benchmark and State of the Art","created":"2017-03-01","cited_by_count":797},{"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":"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":"2212.09849","title":"Dataless Knowledge Fusion by Merging Weights of Language Models","created":"2022-12-19","cited_by_count":387},{"id":"1912.02771","title":"Label-Consistent Backdoor Attacks","created":"2019-12-05","cited_by_count":296},{"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":"2110.14430","title":"Adversarial Neuron Pruning Purifies Backdoored Deep Models","created":"2021-10-27","cited_by_count":235},{"id":"2305.12827","title":"Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models","created":"2023-05-22","cited_by_count":221},{"id":"2208.05592","title":"Patching open-vocabulary models by interpolating weights","created":"2022-08-10","cited_by_count":190},{"id":"2306.14870","title":"Composing Parameter-Efficient Modules with Arithmetic Operations","created":"2023-06-26","cited_by_count":156},{"id":"2206.12654","title":"BackdoorBench: A Comprehensive Benchmark of Backdoor Learning","created":"2022-06-25","cited_by_count":128},{"id":"2402.01109","title":"Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack","created":"2024-02-02","cited_by_count":115},{"id":"2402.02705","title":"Representation Surgery for Multi-Task Model Merging","created":"2024-02-05","cited_by_count":96},{"id":"2302.07027","title":"AdapterSoup: Weight Averaging to Improve Generalization of Pretrained Language Models","created":"2023-02-14","cited_by_count":84},{"id":"2402.09997","title":"LoraRetriever: Input-Aware LoRA Retrieval and Composition for Mixed Tasks in the Wild","created":"2024-02-15","cited_by_count":68},{"id":"2304.11823","title":"Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimization","created":"2023-04-24","cited_by_count":64},{"id":"2409.16167","title":"Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise Clustering","created":"2024-09-24","cited_by_count":59},{"id":"2406.17092","title":"BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models","created":"2024-06-24","cited_by_count":58},{"id":"2209.14981","title":"Stop Wasting My Time! Saving Days of ImageNet and BERT Training with Latest Weight Averaging","created":"2022-09-29","cited_by_count":54},{"id":"2402.12048","title":"Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language Models","created":"2024-02-19","cited_by_count":54},{"id":"2307.10562","title":"Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples","created":"2023-07-20","cited_by_count":43},{"id":"2406.14563","title":"Model Merging and Safety Alignment: One Bad Model Spoils the Bunch","created":"2024-06-20","cited_by_count":43},{"id":"2405.09055","title":"A safety realignment framework via subspace-oriented model fusion for large language models","created":"2024-05-15","cited_by_count":41},{"id":"2312.06173","title":"Concrete Subspace Learning based Interference Elimination for Multi-task Model Fusion","created":"2023-12-11","cited_by_count":37},{"id":"2312.04339","title":"Merging by Matching Models in Task Parameter Subspaces","created":"2023-12-07","cited_by_count":36},{"id":"2408.07362","title":"BadMerging: Backdoor Attacks Against Model Merging","created":"2024-08-14","cited_by_count":34},{"id":"2208.13049","title":"TrojViT: Trojan Insertion in Vision Transformers","created":"2022-08-27","cited_by_count":31},{"id":"2207.04497","title":"One-shot Neural Backdoor Erasing via Adversarial Weight Masking","created":"2022-07-10","cited_by_count":28},{"id":"2402.19334","title":"Here's a Free Lunch: Sanitizing Backdoored Models with Model Merge","created":"2024-02-29","cited_by_count":26},{"id":"2403.00108","title":"LoRATK: LoRA Once, Backdoor Everywhere in the Share-and-Play Ecosystem","created":"2024-02-29","cited_by_count":24},{"id":"2404.05188","title":"Have You Merged My Model? On The Robustness of Large Language Model IP Protection Methods Against Model Merging","created":"2024-04-08","cited_by_count":19},{"id":"2407.19845","title":"BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning","created":"2024-07-29","cited_by_count":19},{"id":"2303.07551","title":"Merging Decision Transformers: Weight Averaging for Forming Multi-Task Policies","created":"2023-03-14","cited_by_count":15},{"id":"2311.08011","title":"Forgetting before Learning: Utilizing Parametric Arithmetic for Knowledge Updating in Large Language Models","created":"2023-11-14","cited_by_count":15},{"id":"2308.11443","title":"Revisiting and Exploring Efficient Fast Adversarial Training via LAW: Lipschitz Regularization and Auto Weight Averaging","created":"2023-08-22","cited_by_count":14},{"id":"2409.13864","title":"Persistent Backdoor Attacks in Continual Learning","created":"2024-09-20","cited_by_count":13},{"id":"2406.09770","title":"Towards Efficient Pareto Set Approximation via Mixture of Experts Based Model Fusion","created":"2024-06-14","cited_by_count":11},{"id":"2303.00215","title":"Single Image Backdoor Inversion via Robust Smoothed Classifiers","created":"2023-03-01","cited_by_count":10},{"id":"2405.17929","title":"Towards Unified Robustness Against Both Backdoor and Adversarial Attacks","created":"2024-05-28","cited_by_count":10},{"id":"2311.11995","title":"BrainWash: A Poisoning Attack to Forget in Continual Learning","created":"2023-11-20","cited_by_count":9},{"id":"2408.10174","title":"SMILE: Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models","created":"2024-08-19","cited_by_count":9},{"id":"2311.17608","title":"Adversarial Robust Memory-Based Continual Learner","created":"2023-11-29","cited_by_count":5},{"id":"2403.09891","title":"Fisher Mask Nodes for Language Model Merging","created":"2024-03-14","cited_by_count":4},{"id":"2307.05476","title":"Fisher-Weighted Merge of Contrastive Learning Models in Sequential Recommendation","created":"2023-07-05","cited_by_count":2},{"id":"2405.03918","title":"Unlearning Backdoor Attacks through Gradient-Based Model Pruning","created":"2024-05-07","cited_by_count":1}],"next_cursor":null}