{"list":"other","total":72,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"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":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2403.08295","title":"Gemma: Open Models Based on Gemini Research and Technology","created":"2024-03-13","cited_by_count":916},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"1312.6120","title":"Exact solutions to the nonlinear dynamics of learning in deep linear neural networks","created":"2013-12-20","cited_by_count":763},{"id":"2402.09353","title":"DoRA: Weight-Decomposed Low-Rank Adaptation","created":"2024-02-14","cited_by_count":758},{"id":"2309.12284","title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","created":"2023-09-21","cited_by_count":735},{"id":"2210.03142","title":"On Distillation of Guided Diffusion Models","created":"2022-10-06","cited_by_count":725},{"id":"2110.07602","title":"P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks","created":"2021-10-14","cited_by_count":689},{"id":"2303.12077","title":"VAD: Vectorized Scene Representation for Efficient Autonomous Driving","created":"2023-03-21","cited_by_count":622},{"id":"2101.03697","title":"RepVGG: Making VGG-style ConvNets Great Again","created":"2021-01-11","cited_by_count":522},{"id":"1511.08458","title":"An Introduction to Convolutional Neural Networks","created":"2015-11-26","cited_by_count":514},{"id":"2403.03507","title":"GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection","created":"2024-03-06","cited_by_count":463},{"id":"2303.10512","title":"AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning","created":"2023-03-18","cited_by_count":357},{"id":"1511.06464","title":"Unitary Evolution Recurrent Neural Networks","created":"2015-11-20","cited_by_count":294},{"id":"2106.14156","title":"Post-Training Quantization for Vision Transformer","created":"2021-06-27","cited_by_count":278},{"id":"2404.02948","title":"PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models","created":"2024-04-03","cited_by_count":269},{"id":"2402.14658","title":"OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement","created":"2024-02-22","cited_by_count":247},{"id":"1512.06473","title":"Quantized Convolutional Neural Networks for Mobile Devices","created":"2015-12-21","cited_by_count":215},{"id":"2310.20624","title":"LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B","created":"2023-10-31","cited_by_count":195},{"id":"2307.08698","title":"Flow Matching in Latent Space","created":"2023-07-17","cited_by_count":160},{"id":"2404.05892","title":"Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence","created":"2024-04-08","cited_by_count":159},{"id":"2110.08727","title":"Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation","created":"2021-10-17","cited_by_count":152},{"id":"2109.05687","title":"Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning","created":"2021-09-13","cited_by_count":146},{"id":"2004.03829","title":"Exploring Versatile Generative Language Model Via Parameter-Efficient Transfer Learning","created":"2020-04-08","cited_by_count":139},{"id":"2110.14038","title":"Robustness of Graph Neural Networks at Scale","created":"2021-10-26","cited_by_count":100},{"id":"1611.00035","title":"Full-Capacity Unitary Recurrent Neural Networks","created":"2016-10-31","cited_by_count":94},{"id":"1709.06079","title":"Orthogonal Weight Normalization: Solution to Optimization over Multiple Dependent Stiefel Manifolds in Deep Neural Networks","created":"2017-09-16","cited_by_count":92},{"id":"2403.17919","title":"LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning","created":"2024-03-26","cited_by_count":89},{"id":"2403.05175","title":"Continual Learning and Catastrophic Forgetting","created":"2024-03-08","cited_by_count":77},{"id":"2402.17376","title":"Accelerating Diffusion Sampling with Optimized Time Steps","created":"2024-02-27","cited_by_count":67},{"id":"1910.02212","title":"Symbiotic Graph Neural Networks for 3D Skeleton-based Human Action Recognition and Motion Prediction","created":"2019-10-05","cited_by_count":50},{"id":"2407.01079","title":"On Statistical Rates and Provably Efficient Criteria of Latent Diffusion Transformers (DiTs)","created":"2024-07-01","cited_by_count":40},{"id":"2406.01775","title":"OLoRA: Orthonormal Low-Rank Adaptation of Large Language Models","created":"2024-06-03","cited_by_count":39},{"id":"2404.09610","title":"LoRA Dropout as a Sparsity Regularizer for Overfitting Control","created":"2024-04-15","cited_by_count":35},{"id":"2210.00102","title":"MLPInit: Embarrassingly Simple GNN Training Acceleration with MLP Initialization","created":"2022-09-30","cited_by_count":31},{"id":"2402.13973","title":"Linear-Time Graph Neural Networks for Scalable Recommendations","created":"2024-02-21","cited_by_count":31},{"id":"2201.06885","title":"Evidence-aware Fake News Detection with Graph Neural Networks","created":"2022-01-18","cited_by_count":30},{"id":"2403.07353","title":"Graph Unlearning with Efficient Partial Retraining","created":"2024-03-12","cited_by_count":20},{"id":"2302.01503","title":"LazyGNN: Large-Scale Graph Neural Networks via Lazy Propagation","created":"2023-02-03","cited_by_count":16},{"id":"2201.12741","title":"GARNET: Reduced-Rank Topology Learning for Robust and Scalable Graph Neural Networks","created":"2022-01-30","cited_by_count":14},{"id":"2311.13745","title":"Improved Sample Complexity Bounds for Diffusion Model Training","created":"2023-11-23","cited_by_count":14},{"id":"2408.09212","title":"Scalable and Certifiable Graph Unlearning: Overcoming the Approximation Error Barrier","created":"2024-08-17","cited_by_count":14},{"id":"2210.10737","title":"RSC: Accelerating Graph Neural Networks Training via Randomized Sparse Computations","created":"2022-10-19","cited_by_count":12},{"id":"2109.13995","title":"IGLU: Efficient GCN Training via Lazy Updates","created":"2021-09-28","cited_by_count":7},{"id":"2110.11583","title":"EvoGAN: An Evolutionary Computation Assisted GAN","created":"2021-10-22","cited_by_count":6},{"id":"1801.00905","title":"Neural Networks in Adversarial Setting and Ill-Conditioned Weight Space","created":"2018-01-03","cited_by_count":5}],"next_cursor":null}