{"list":"other","total":55,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"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":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"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":"2401.14196","title":"DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence","created":"2024-01-25","cited_by_count":1181},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120},{"id":"1711.02257","title":"GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks","created":"2017-11-07","cited_by_count":834},{"id":"2306.01708","title":"TIES-Merging: Resolving Interference When Merging Models","created":"2023-06-02","cited_by_count":818},{"id":"1602.06023","title":"Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond","created":"2016-02-19","cited_by_count":812},{"id":"1703.00121","title":"Remote Sensing Image Scene Classification: Benchmark and State of the Art","created":"2017-03-01","cited_by_count":797},{"id":"2110.08193","title":"BBQ: A Hand-Built Bias Benchmark for Question Answering","created":"2021-10-15","cited_by_count":701},{"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":"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":"1802.10026","title":"Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs","created":"2018-02-27","cited_by_count":588},{"id":"2104.10350","title":"Carbon Emissions and Large Neural Network Training","created":"2021-04-21","cited_by_count":567},{"id":"2002.06440","title":"Federated Learning with Matched Averaging","created":"2020-02-15","cited_by_count":564},{"id":"2209.04836","title":"Git Re-Basin: Merging Models modulo Permutation Symmetries","created":"2022-09-11","cited_by_count":471},{"id":"2110.14048","title":"Conflict-Averse Gradient Descent for Multi-task Learning","created":"2021-10-26","cited_by_count":459},{"id":"2212.09849","title":"Dataless Knowledge Fusion by Merging Weights of Language Models","created":"2022-12-19","cited_by_count":387},{"id":"2307.13269","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","created":"2023-07-25","cited_by_count":364},{"id":"1803.00885","title":"Essentially No Barriers in Neural Network Energy Landscape","created":"2018-03-02","cited_by_count":330},{"id":"2202.01169","title":"Unified Scaling Laws for Routed Language Models","created":"2022-02-02","cited_by_count":253},{"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":"1910.05653","title":"Model Fusion via Optimal Transport","created":"2019-10-12","cited_by_count":219},{"id":"2202.01017","title":"Multi-Task Learning as a Bargaining Game","created":"2022-02-02","cited_by_count":215},{"id":"2306.14870","title":"Composing Parameter-Efficient Modules with Arithmetic Operations","created":"2023-06-26","cited_by_count":156},{"id":"1904.08918","title":"Attentive Single-Tasking of Multiple Tasks","created":"2019-04-18","cited_by_count":148},{"id":"2403.07816","title":"Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM","created":"2024-03-12","cited_by_count":109},{"id":"2402.02705","title":"Representation Surgery for Multi-Task Model Merging","created":"2024-02-05","cited_by_count":96},{"id":"2402.00433","title":"Merging Multi-Task Models via Weight-Ensembling Mixture of Experts","created":"2024-02-01","cited_by_count":85},{"id":"2310.04742","title":"Parameter Efficient Multi-task Model Fusion with Partial Linearization","created":"2023-10-07","cited_by_count":65},{"id":"2103.03014","title":"Lost in Pruning: The Effects of Pruning Neural Networks beyond Test Accuracy","created":"2021-03-04","cited_by_count":62},{"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":"2310.01542","title":"Fusing Models with Complementary Expertise","created":"2023-10-02","cited_by_count":46},{"id":"2301.12618","title":"ForkMerge: Mitigating Negative Transfer in Auxiliary-Task Learning","created":"2023-01-30","cited_by_count":28},{"id":"2306.09719","title":"Pushing the Limits of ChatGPT on NLP Tasks","created":"2023-06-16","cited_by_count":27},{"id":"2406.09072","title":"Living in the Moment: Can Large Language Models Grasp Co-Temporal Reasoning?","created":"2024-06-13","cited_by_count":25},{"id":"2308.02066","title":"Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing with Non-Learnable Primitives","created":"2023-08-03","cited_by_count":18},{"id":"2406.07001","title":"Mitigating Boundary Ambiguity and Inherent Bias for Text Classification in the Era of Large Language Models","created":"2024-06-11","cited_by_count":9},{"id":"2310.01886","title":"BYOM: Building Your Own Multi-Task Model For Free","created":"2023-10-03","cited_by_count":5}],"next_cursor":null}