{"list":"other","total":60,"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":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"1708.07747","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","created":"2017-08-25","cited_by_count":4349},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"2103.03230","title":"Barlow Twins: Self-Supervised Learning via Redundancy Reduction","created":"2021-03-04","cited_by_count":1838},{"id":"1905.00414","title":"Similarity of Neural Network Representations Revisited","created":"2019-05-01","cited_by_count":1755},{"id":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"1709.00029","title":"EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification","created":"2017-08-31","cited_by_count":1496},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"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":"1805.12471","title":"Neural Network Acceptability Judgments","created":"2018-05-31","cited_by_count":958},{"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":"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":"2308.09583","title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","created":"2023-08-18","cited_by_count":625},{"id":"2111.09832","title":"Merging Models with Fisher-Weighted Averaging","created":"2021-11-18","cited_by_count":621},{"id":"1806.03962","title":"Rotation Equivariant CNNs for Digital Pathology","created":"2018-06-08","cited_by_count":422},{"id":"2212.09849","title":"Dataless Knowledge Fusion by Merging Weights of Language Models","created":"2022-12-19","cited_by_count":387},{"id":"1307.0414","title":"Challenges in Representation Learning: A report on three machine learning contests","created":"2013-07-01","cited_by_count":302},{"id":"2310.02575","title":"AdaMerging: Adaptive Model Merging for Multi-Task Learning","created":"2023-10-04","cited_by_count":252},{"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":"2311.13600","title":"ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAs","created":"2023-11-22","cited_by_count":194},{"id":"2403.13257","title":"Arcee's MergeKit: A Toolkit for Merging Large Language Models","created":"2024-03-20","cited_by_count":194},{"id":"2412.00081","title":"Task Singular Vectors: Reducing Task Interference in Model Merging","created":"2024-11-26","cited_by_count":147},{"id":"2405.07813","title":"Localizing Task Information for Improved Model Merging and Compression","created":"2024-05-13","cited_by_count":131},{"id":"2406.15479","title":"Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging","created":"2024-06-17","cited_by_count":116},{"id":"2405.17461","title":"EMR-Merging: Tuning-Free High-Performance Model Merging","created":"2024-05-23","cited_by_count":110},{"id":"2402.02705","title":"Representation Surgery for Multi-Task Model Merging","created":"2024-02-05","cited_by_count":96},{"id":"2502.04959","title":"No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces","created":"2025-02-07","cited_by_count":96},{"id":"2410.02396","title":"Parameter Competition Balancing for Model Merging","created":"2024-10-03","cited_by_count":72},{"id":"2407.06322","title":"MagMax: Leveraging Model Merging for Seamless Continual Learning","created":"2024-07-08","cited_by_count":67},{"id":"2408.07990","title":"FuseChat: Knowledge Fusion of Chat Models","created":"2024-08-15","cited_by_count":55},{"id":"2402.12048","title":"Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language Models","created":"2024-02-19","cited_by_count":54},{"id":"2311.14479","title":"Controlled Text Generation via Language Model Arithmetic","created":"2023-11-24","cited_by_count":51},{"id":"2408.13656","title":"Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic","created":"2024-08-24","cited_by_count":50},{"id":"2309.15564","title":"Jointly Training Large Autoregressive Multimodal Models","created":"2023-09-27","cited_by_count":32},{"id":"2311.02428","title":"Task Arithmetic with LoRA for Continual Learning","created":"2023-11-04","cited_by_count":32},{"id":"2403.04861","title":"A Survey of Lottery Ticket Hypothesis","created":"2024-03-07","cited_by_count":24},{"id":"2505.06977","title":"CAT Merging: A Training-Free Approach for Resolving Conflicts in Model Merging","created":"2025-05-11","cited_by_count":23},{"id":"2410.03782","title":"DaWin: Training-free Dynamic Weight Interpolation for Robust Adaptation","created":"2024-10-03","cited_by_count":19},{"id":"2503.00938","title":"From Poses to Identity: Training-Free Person Re-Identification via Feature Centralization","created":"2025-03-02","cited_by_count":17},{"id":"2501.15065","title":"Task Arithmetic in Trust Region: A Training-Free Model Merging Approach to Navigate Knowledge Conflicts","created":"2025-01-25","cited_by_count":13},{"id":"2310.18823","title":"Successfully Applying Lottery Ticket Hypothesis to Diffusion Model","created":"2023-10-28","cited_by_count":11},{"id":"2502.10339","title":"STAR: Spectral Truncation and Rescale for Model Merging","created":"2025-02-14","cited_by_count":11},{"id":"2503.08998","title":"From Task-Specific Models to Unified Systems: A Review of Model Merging Approaches","created":"2025-03-12","cited_by_count":11},{"id":"2505.18713","title":"Neural Parameter Search for Slimmer Fine-Tuned Models and Better Transfer","created":"2025-05-24","cited_by_count":11},{"id":"2506.16506","title":"Subspace-Boosted Model Merging","created":"2025-06-19","cited_by_count":9},{"id":"2509.09263","title":"DATE: Dynamic Absolute Time Enhancement for Long Video Understanding","created":"2025-09-11","cited_by_count":9},{"id":"2512.03575","title":"UniComp: Rethinking Video Compression Through Informational Uniqueness","created":"2025-12-03","cited_by_count":7},{"id":"2412.11375","title":"Text and Image Are Mutually Beneficial: Enhancing Training-Free Few-Shot Classification with CLIP","created":"2024-12-16","cited_by_count":6},{"id":"2511.02685","title":"Modality-Transition Representation Learning for Visible-Infrared Person Re-Identification","created":"2025-11-04","cited_by_count":6},{"id":"2504.11798","title":"Neighbor-Based Feature and Index Enhancement for Person Re-Identification","created":"2025-04-16","cited_by_count":5},{"id":"2508.05316","title":"Divide-and-Conquer for Enhancing Unlabeled Learning, Stability, and Plasticity in Semi-supervised Continual Learning","created":"2025-08-07","cited_by_count":3},{"id":"2512.19320","title":"MAGIC: Achieving Superior Model Merging via Magnitude Calibration","created":"2025-12-22","cited_by_count":2}],"next_cursor":null}