{"list":"other","total":51,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"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":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"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":"2212.10511","title":"When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories","created":"2022-12-20","cited_by_count":1128},{"id":"2210.03350","title":"Measuring and Narrowing the Compositionality Gap in Language Models","created":"2022-10-07","cited_by_count":1075},{"id":"2108.00573","title":"MuSiQue: Multihop Questions via Single-hop Question Composition","created":"2021-08-02","cited_by_count":916},{"id":"2406.18665","title":"RouteLLM: Learning to Route LLMs with Preference Data","created":"2024-06-26","cited_by_count":682},{"id":"2207.01848","title":"TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second","created":"2022-07-05","cited_by_count":674},{"id":"1908.00709","title":"AutoML: A Survey of the State-of-the-Art","created":"2019-08-02","cited_by_count":390},{"id":"2403.12031","title":"RouterBench: A Benchmark for Multi-LLM Routing System","created":"2024-03-18","cited_by_count":238},{"id":"1902.03545","title":"Task2Vec: Task Embedding for Meta-Learning","created":"2019-02-10","cited_by_count":205},{"id":"2002.12462","title":"LEEP: A New Measure to Evaluate Transferability of Learned Representations","created":"2020-02-27","cited_by_count":188},{"id":"2102.11005","title":"LogME: Practical Assessment of Pre-trained Models for Transfer Learning","created":"2021-02-22","cited_by_count":172},{"id":"2410.03834","title":"GraphRouter: A Graph-based Router for LLM Selections","created":"2024-10-04","cited_by_count":165},{"id":"2501.15383","title":"Qwen2.5-1M Technical Report","created":"2025-01-26","cited_by_count":164},{"id":"1908.08142","title":"Transferability and Hardness of Supervised Classification Tasks","created":"2019-08-21","cited_by_count":127},{"id":"2002.06716","title":"Predicting trends in the quality of state-of-the-art neural networks without access to training or testing data","created":"2020-02-17","cited_by_count":115},{"id":"2002.11448","title":"Predicting Neural Network Accuracy from Weights","created":"2020-02-26","cited_by_count":110},{"id":"2504.03624","title":"Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models","created":"2025-04-04","cited_by_count":100},{"id":"2409.19886","title":"RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Models","created":"2024-09-30","cited_by_count":88},{"id":"1904.12058","title":"Inductive Matrix Completion Based on Graph Neural Networks","created":"2019-04-26","cited_by_count":86},{"id":"2212.10082","title":"An Information-Theoretic Approach to Transferability in Task Transfer Learning","created":"2022-12-20","cited_by_count":81},{"id":"2506.09033","title":"Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning","created":"2025-06-10","cited_by_count":72},{"id":"2209.14733","title":"Hyper-Representations as Generative Models: Sampling Unseen Neural Network Weights","created":"2022-09-29","cited_by_count":64},{"id":"2103.13843","title":"OTCE: A Transferability Metric for Cross-Domain Cross-Task Representations","created":"2021-03-25","cited_by_count":62},{"id":"2503.10657","title":"RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs","created":"2025-03-08","cited_by_count":61},{"id":"2111.12780","title":"Transferability Estimation using Bhattacharyya Class Separability","created":"2021-11-24","cited_by_count":54},{"id":"2011.11200","title":"Ranking Neural Checkpoints","created":"2020-11-23","cited_by_count":51},{"id":"2004.14356","title":"AxCell: Automatic Extraction of Results from Machine Learning Papers","created":"2020-04-29","cited_by_count":48},{"id":"2102.00084","title":"A linearized framework and a new benchmark for model selection for fine-tuning","created":"2021-01-29","cited_by_count":41},{"id":"2310.06116","title":"OptiMUS: Optimization Modeling Using MIP Solvers and large language models","created":"2023-10-09","cited_by_count":39},{"id":"1306.0626","title":"Provable Inductive Matrix Completion","created":"2013-06-04","cited_by_count":32},{"id":"2306.03900","title":"Model Spider: Learning to Rank Pre-Trained Models Efficiently","created":"2023-06-06","cited_by_count":32},{"id":"2502.13458","title":"ThinkGuard: Deliberative Slow Thinking Leads to Cautious Guardrails","created":"2025-02-19","cited_by_count":31},{"id":"2203.05126","title":"PACTran: PAC-Bayesian Metrics for Estimating the Transferability of Pretrained Models to Classification Tasks","created":"2022-03-10","cited_by_count":30},{"id":"2503.10633","title":"We Should Chart an Atlas of All the World's Models","created":"2025-03-13","cited_by_count":25},{"id":"2505.19616","title":"Diagnosing and Mitigating Modality Interference in Multimodal Large Language Models","created":"2025-05-26","cited_by_count":19},{"id":"2508.07918","title":"RSVLM-QA: A Benchmark Dataset for Remote Sensing Vision Language Model-based Question Answering","created":"2025-08-11","cited_by_count":17},{"id":"2412.15547","title":"NGQA: A Nutritional Graph Question Answering Benchmark for Personalized Health-aware Nutritional Reasoning","created":"2024-12-20","cited_by_count":16},{"id":"2509.24496","title":"LLM DNA: Tracing Model Evolution via Functional Representations","created":"2025-09-29","cited_by_count":15},{"id":"2206.08476","title":"Zero-Shot AutoML with Pretrained Models","created":"2022-06-16","cited_by_count":14},{"id":"2512.02306","title":"OmniGuard: Unified Omni-Modal Guardrails with Deliberate Reasoning","created":"2025-12-02","cited_by_count":7},{"id":"2510.02096","title":"Learning Model Representations Using Publicly Available Model Hubs","created":"2025-10-02","cited_by_count":4},{"id":"2412.16251","title":"Know2Vec: A Black-Box Proxy for Neural Network Retrieval","created":"2024-12-20","cited_by_count":2},{"id":"2406.07536","title":"Towards Fundamentally Scalable Model Selection: Asymptotically Fast Update and Selection","created":"2024-06-11","cited_by_count":1}],"next_cursor":null}