{"list":"other","total":89,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"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":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120},{"id":"2306.01708","title":"TIES-Merging: Resolving Interference When Merging Models","created":"2023-06-02","cited_by_count":818},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","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":"1802.10026","title":"Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs","created":"2018-02-27","cited_by_count":588},{"id":"2209.04836","title":"Git Re-Basin: Merging Models modulo Permutation Symmetries","created":"2022-09-11","cited_by_count":471},{"id":"2111.03930","title":"Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling","created":"2021-11-06","cited_by_count":431},{"id":"2212.09849","title":"Dataless Knowledge Fusion by Merging Weights of Language Models","created":"2022-12-19","cited_by_count":387},{"id":"2008.11687","title":"What is being transferred in transfer learning?","created":"2020-08-26","cited_by_count":368},{"id":"2402.07865","title":"Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models","created":"2024-02-12","cited_by_count":339},{"id":"2210.07183","title":"Visual Classification via Description from Large Language Models","created":"2022-10-13","cited_by_count":336},{"id":"2209.03320","title":"What does a platypus look like? Generating customized prompts for zero-shot image classification","created":"2022-09-07","cited_by_count":267},{"id":"2106.05237","title":"Knowledge distillation: A good teacher is patient and consistent","created":"2021-06-09","cited_by_count":259},{"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":"2312.00886","title":"Nash Learning from Human Feedback","created":"2023-12-01","cited_by_count":224},{"id":"2403.13187","title":"Evolutionary Optimization of Model Merging Recipes","created":"2024-03-19","cited_by_count":208},{"id":"2403.13257","title":"Arcee's MergeKit: A Toolkit for Merging Large Language Models","created":"2024-03-20","cited_by_count":194},{"id":"2208.03306","title":"Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models","created":"2022-08-05","cited_by_count":191},{"id":"2208.05592","title":"Patching open-vocabulary models by interpolating weights","created":"2022-08-10","cited_by_count":190},{"id":"2309.06256","title":"Mitigating the Alignment Tax of RLHF","created":"2023-09-12","cited_by_count":183},{"id":"2205.09739","title":"Diverse Weight Averaging for Out-of-Distribution Generalization","created":"2022-05-19","cited_by_count":148},{"id":"2401.12187","title":"WARM: On the Benefits of Weight Averaged Reward Models","created":"2024-01-22","cited_by_count":147},{"id":"2312.06795","title":"Model Breadcrumbs: Scaling Multi-Task Model Merging with Sparse Masks","created":"2023-12-11","cited_by_count":133},{"id":"2405.07813","title":"Localizing Task Information for Improved Model Merging and Compression","created":"2024-05-13","cited_by_count":131},{"id":"2403.08763","title":"Simple and Scalable Strategies to Continually Pre-train Large Language Models","created":"2024-03-13","cited_by_count":127},{"id":"2205.11388","title":"StreamingQA: A Benchmark for Adaptation to New Knowledge over Time in Question Answering Models","created":"2022-05-23","cited_by_count":126},{"id":"2410.19735","title":"Model merging with SVD to tie the Knots","created":"2024-10-25","cited_by_count":122},{"id":"2211.16198","title":"SuS-X: Training-Free Name-Only Transfer of Vision-Language Models","created":"2022-11-28","cited_by_count":119},{"id":"2302.04476","title":"Towards Geospatial Foundation Models via Continual Pretraining","created":"2023-02-09","cited_by_count":109},{"id":"2306.07282","title":"Waffling around for Performance: Visual Classification with Random Words and Broad Concepts","created":"2023-06-12","cited_by_count":101},{"id":"2402.02705","title":"Representation Surgery for Multi-Task Model Merging","created":"2024-02-05","cited_by_count":96},{"id":"2201.06289","title":"The CLEAR Benchmark: Continual LEArning on Real-World Imagery","created":"2022-01-17","cited_by_count":93},{"id":"2403.19522","title":"Model Stock: All we need is just a few fine-tuned models","created":"2024-03-28","cited_by_count":92},{"id":"2406.11617","title":"DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling","created":"2024-06-17","cited_by_count":81},{"id":"2404.04125","title":"No \"Zero-Shot\" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance","created":"2024-04-04","cited_by_count":75},{"id":"2108.09020","title":"Online Continual Learning with Natural Distribution Shifts: An Empirical Study with Visual Data","created":"2021-08-20","cited_by_count":69},{"id":"2402.02992","title":"Decoding-time Realignment of Language Models","created":"2024-02-05","cited_by_count":67},{"id":"2407.06322","title":"MagMax: Leveraging Model Merging for Seamless Continual Learning","created":"2024-07-08","cited_by_count":67},{"id":"2205.00329","title":"Continual Learning with Foundation Models: An Empirical Study of Latent Replay","created":"2022-04-30","cited_by_count":61},{"id":"2303.11165","title":"Computationally Budgeted Continual Learning: What Does Matter?","created":"2023-03-20","cited_by_count":61},{"id":"2402.17400","title":"Investigating Continual Pretraining in Large Language Models: Insights and Implications","created":"2024-02-27","cited_by_count":57},{"id":"2404.09656","title":"Learn Your Reference Model for Real Good Alignment","created":"2024-04-15","cited_by_count":57},{"id":"2410.03617","title":"What Matters for Model Merging at Scale?","created":"2024-10-04","cited_by_count":55},{"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":"2212.01378","title":"ColD Fusion: Collaborative Descent for Distributed Multitask Finetuning","created":"2022-12-02","cited_by_count":52},{"id":"2304.14933","title":"An Empirical Study of Multimodal Model Merging","created":"2023-04-28","cited_by_count":52},{"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":"2408.13656","title":"Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic","created":"2024-08-24","cited_by_count":50},{"id":"2406.16768","title":"WARP: On the Benefits of Weight Averaged Rewarded Policies","created":"2024-06-24","cited_by_count":45},{"id":"2407.06089","title":"Merge, Ensemble, and Cooperate! A Survey on Collaborative Strategies in the Era of Large Language Models","created":"2024-07-08","cited_by_count":44},{"id":"2410.17146","title":"LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging","created":"2024-10-22","cited_by_count":41},{"id":"2310.16226","title":"TiC-CLIP: Continual Training of CLIP Models","created":"2023-10-24","cited_by_count":38},{"id":"2306.03241","title":"Early Weight Averaging meets High Learning Rates for LLM Pre-training","created":"2023-06-05","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":"2407.08699","title":"Mitigating Catastrophic Forgetting in Language Transfer via Model Merging","created":"2024-07-11","cited_by_count":36},{"id":"2312.13401","title":"Time is Encoded in the Weights of Finetuned Language Models","created":"2023-12-20","cited_by_count":33},{"id":"2305.09253","title":"Online Continual Learning Without the Storage Constraint","created":"2023-05-16","cited_by_count":29},{"id":"2211.00107","title":"Where to start? Analyzing the potential value of intermediate models","created":"2022-10-31","cited_by_count":23},{"id":"2410.21804","title":"Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Merging","created":"2024-10-29","cited_by_count":23},{"id":"2411.18729","title":"Multi-Task Model Merging via Adaptive Weight Disentanglement","created":"2024-11-27","cited_by_count":22},{"id":"2404.09447","title":"kNN-CLIP: Retrieval Enables Training-Free Segmentation on Continually Expanding Large Vocabularies","created":"2024-04-15","cited_by_count":20},{"id":"2211.03186","title":"Momentum-based Weight Interpolation of Strong Zero-Shot Models for Continual Learning","created":"2022-11-06","cited_by_count":19},{"id":"2410.03782","title":"DaWin: Training-free Dynamic Weight Interpolation for Robust Adaptation","created":"2024-10-03","cited_by_count":19},{"id":"2411.18674","title":"Active Data Curation Effectively Distills Large-Scale Multimodal Models","created":"2024-11-27","cited_by_count":19},{"id":"2211.11747","title":"NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research","created":"2022-11-15","cited_by_count":18},{"id":"2407.02447","title":"PLeaS -- Merging Models with Permutations and Least Squares","created":"2024-07-02","cited_by_count":16},{"id":"2311.07682","title":"Fuse to Forget: Bias Reduction and Selective Memorization through Model Fusion","created":"2023-11-13","cited_by_count":13},{"id":"2409.18314","title":"Realistic Evaluation of Model Merging for Compositional Generalization","created":"2024-09-26","cited_by_count":12},{"id":"2411.03055","title":"ATM: Improving Model Merging by Alternating Tuning and Merging","created":"2024-11-05","cited_by_count":11},{"id":"2410.06084","title":"Diversity-Rewarded CFG Distillation","created":"2024-10-08","cited_by_count":9},{"id":"2406.09384","title":"Reflecting on the State of Rehearsal-free Continual Learning with Pretrained Models","created":"2024-06-13","cited_by_count":8},{"id":"2410.12766","title":"The Non-Local Model Merging Problem: Permutation Symmetries and Variance Collapse","created":"2024-10-16","cited_by_count":8},{"id":"2211.12092","title":"Linear Interpolation In Parameter Space is Good Enough for Fine-Tuned Language Models","created":"2022-11-22","cited_by_count":7},{"id":"2411.02207","title":"Collective Model Intelligence Requires Compatible Specialization","created":"2024-11-04","cited_by_count":7},{"id":"2410.19925","title":"Improving Multimodal Large Language Models Using Continual Learning","created":"2024-10-25","cited_by_count":5},{"id":"2407.03641","title":"Learning Scalable Model Soup on a Single GPU: An Efficient Subspace Training Strategy","created":"2024-07-04","cited_by_count":3},{"id":"2411.15099","title":"Context-Aware Multimodal Pretraining","created":"2024-11-22","cited_by_count":3}],"next_cursor":null}