{"list":"other","total":60,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2308.12966","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","created":"2023-08-24","cited_by_count":2224},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"2202.12837","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","created":"2022-02-25","cited_by_count":1434},{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242},{"id":"2303.16199","title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","created":"2023-03-28","cited_by_count":781},{"id":"2307.05782","title":"Large Language Models","created":"2023-07-11","cited_by_count":780},{"id":"2304.15010","title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","created":"2023-04-28","cited_by_count":602},{"id":"2309.00071","title":"YaRN: Efficient Context Window Extension of Large Language Models","created":"2023-08-31","cited_by_count":601},{"id":"2102.11174","title":"Linear Transformers Are Secretly Fast Weight Programmers","created":"2021-02-22","cited_by_count":502},{"id":"1911.03894","title":"CamemBERT: a Tasty French Language Model","created":"2019-11-10","cited_by_count":368},{"id":"2306.09927","title":"Trained Transformers Learn Linear Models In-Context","created":"2023-06-16","cited_by_count":337},{"id":"2402.13753","title":"LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens","created":"2024-02-21","cited_by_count":313},{"id":"2305.15408","title":"Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective","created":"2023-05-24","cited_by_count":294},{"id":"2402.17762","title":"Massive Activations in Large Language Models","created":"2024-02-27","cited_by_count":294},{"id":"2210.10749","title":"Transformers Learn Shortcuts to Automata","created":"2022-10-19","cited_by_count":268},{"id":"2309.12307","title":"LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models","created":"2023-09-21","cited_by_count":244},{"id":"2403.09611","title":"MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training","created":"2024-03-14","cited_by_count":232},{"id":"2311.10723","title":"Large Language Models in Finance: A Survey","created":"2023-09-28","cited_by_count":226},{"id":"2207.00729","title":"The Parallelism Tradeoff: Limitations of Log-Precision Transformers","created":"2022-07-02","cited_by_count":193},{"id":"2403.07183","title":"Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews","created":"2024-03-11","cited_by_count":164},{"id":"2209.04881","title":"On The Computational Complexity of Self-Attention","created":"2022-09-11","cited_by_count":139},{"id":"2401.01325","title":"LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning","created":"2024-01-02","cited_by_count":136},{"id":"2306.02896","title":"Representational Strengths and Limitations of Transformers","created":"2023-06-05","cited_by_count":133},{"id":"2305.01625","title":"Unlimiformer: Long-Range Transformers with Unlimited Length Input","created":"2023-05-02","cited_by_count":128},{"id":"2402.04347","title":"The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry","created":"2024-02-06","cited_by_count":120},{"id":"2302.13214","title":"Fast Attention Requires Bounded Entries","created":"2023-02-26","cited_by_count":102},{"id":"2310.01082","title":"Linear attention is (maybe) all you need (to understand transformer optimization)","created":"2023-10-02","cited_by_count":98},{"id":"1706.03175","title":"Recovery Guarantees for One-hidden-layer Neural Networks","created":"2017-06-10","cited_by_count":94},{"id":"1906.09777","title":"A Tensorized Transformer for Language Modeling","created":"2019-06-24","cited_by_count":86},{"id":"2310.05869","title":"HyperAttention: Long-context Attention in Near-Linear Time","created":"2023-10-09","cited_by_count":85},{"id":"2302.02451","title":"KDEformer: Accelerating Transformers via Kernel Density Estimation","created":"2023-02-05","cited_by_count":58},{"id":"2303.09136","title":"A Short Survey of Viewing Large Language Models in Legal Aspect","created":"2023-03-16","cited_by_count":52},{"id":"2404.08801","title":"Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length","created":"2024-04-12","cited_by_count":46},{"id":"2310.04064","title":"How to Capture Higher-order Correlations? Generalizing Matrix Softmax Attention to Kronecker Computation","created":"2023-10-06","cited_by_count":44},{"id":"1708.04181","title":"Tensor Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Tensors via Convex Optimization","created":"2017-08-14","cited_by_count":35},{"id":"2204.04667","title":"Linear Complexity Randomized Self-attention Mechanism","created":"2022-04-10","cited_by_count":31},{"id":"2302.11068","title":"Low Rank Matrix Completion via Robust Alternating Minimization in Nearly Linear Time","created":"2023-02-21","cited_by_count":31},{"id":"2402.04497","title":"The Fine-Grained Complexity of Gradient Computation for Training Large Language Models","created":"2024-02-07","cited_by_count":30},{"id":"1608.05749","title":"Solving a Mixture of Many Random Linear Equations by Tensor Decomposition and Alternating Minimization","created":"2016-08-19","cited_by_count":26},{"id":"2011.02466","title":"Algorithms and Hardness for Linear Algebra on Geometric Graphs","created":"2020-11-04","cited_by_count":22},{"id":"1908.01341","title":"SF-Net: Structured Feature Network for Continuous Sign Language Recognition","created":"2019-08-04","cited_by_count":20},{"id":"2205.06249","title":"Optimal-Degree Polynomial Approximations for Exponentials and Gaussian Kernel Density Estimation","created":"2022-05-12","cited_by_count":19},{"id":"2110.02667","title":"Attentive Walk-Aggregating Graph Neural Networks","created":"2021-10-06","cited_by_count":10},{"id":"1507.01784","title":"Rethinking LDA: moment matching for discrete ICA","created":"2015-07-07","cited_by_count":5},{"id":"1701.04043","title":"Iterative Block Tensor Singular Value Thresholding for Extraction of Low Rank Component of Image Data","created":"2017-01-15","cited_by_count":4},{"id":"1610.00843","title":"The Search Problem in Mixture Models","created":"2016-10-04","cited_by_count":3}],"next_cursor":null}