{"list":"other","total":55,"rows":[{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"id":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"2405.09818","title":"Chameleon: Mixed-Modal Early-Fusion Foundation Models","created":"2024-05-16","cited_by_count":927},{"id":"1511.02283","title":"Generation and Comprehension of Unambiguous Object Descriptions","created":"2015-11-07","cited_by_count":904},{"id":"2409.18869","title":"Emu3: Next-Token Prediction is All You Need","created":"2024-09-27","cited_by_count":781},{"id":"2406.06525","title":"Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation","created":"2024-06-10","cited_by_count":777},{"id":"2310.01728","title":"Time-LLM: Time Series Forecasting by Reprogramming Large Language Models","created":"2023-10-03","cited_by_count":700},{"id":"1702.08165","title":"Reinforcement Learning with Deep Energy-Based Policies","created":"2017-02-27","cited_by_count":669},{"id":"2310.05737","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","created":"2023-10-09","cited_by_count":640},{"id":"2310.08491","title":"Prometheus: Inducing Fine-grained Evaluation Capability in Language Models","created":"2023-10-12","cited_by_count":575},{"id":"2005.00341","title":"Jukebox: A Generative Model for Music","created":"2020-04-30","cited_by_count":542},{"id":"2310.07704","title":"Ferret: Refer and Ground Anything Anywhere at Any Granularity","created":"2023-10-11","cited_by_count":509},{"id":"2310.07820","title":"Large Language Models Are Zero-Shot Time Series Forecasters","created":"2023-10-11","cited_by_count":500},{"id":"2403.13787","title":"RewardBench: Evaluating Reward Models for Language Modeling","created":"2024-03-20","cited_by_count":499},{"id":"2303.05511","title":"Scaling up GANs for Text-to-Image Synthesis","created":"2023-03-09","cited_by_count":492},{"id":"2405.01535","title":"Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models","created":"2024-05-02","cited_by_count":446},{"id":"2311.06242","title":"Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks","created":"2023-11-10","cited_by_count":410},{"id":"2310.01377","title":"UltraFeedback: Boosting Language Models with Scaled AI Feedback","created":"2023-10-02","cited_by_count":406},{"id":"2101.06840","title":"ZeRO-Offload: Democratizing Billion-Scale Model Training","created":"2021-01-18","cited_by_count":341},{"id":"2206.11251","title":"Behavior Transformers: Cloning $k$ modes with one stone","created":"2022-06-22","cited_by_count":304},{"id":"2406.08673","title":"HelpSteer2: Open-source dataset for training top-performing reward models","created":"2024-06-12","cited_by_count":236},{"id":"2303.06674","title":"Universal Instance Perception as Object Discovery and Retrieval","created":"2023-03-12","cited_by_count":192},{"id":"2310.01218","title":"Making LLaMA SEE and Draw with SEED Tokenizer","created":"2023-10-02","cited_by_count":185},{"id":"2004.00010","title":"The Discrete Gaussian for Differential Privacy","created":"2020-03-31","cited_by_count":135},{"id":"2304.02015","title":"How well do Large Language Models perform in Arithmetic tasks?","created":"2023-03-16","cited_by_count":130},{"id":"2102.06387","title":"The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation","created":"2021-02-12","cited_by_count":128},{"id":"2404.07973","title":"Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models","created":"2024-04-11","cited_by_count":97},{"id":"1808.00508","title":"Neural Arithmetic Logic Units","created":"2018-08-01","cited_by_count":70},{"id":"2310.06213","title":"GeoLLM: Extracting Geospatial Knowledge from Large Language Models","created":"2023-10-10","cited_by_count":64},{"id":"2404.07544","title":"From Words to Numbers: Your Large Language Model Is Secretly A Capable Regressor When Given In-Context Examples","created":"2024-04-11","cited_by_count":57},{"id":"2406.20095","title":"LLaRA: Supercharging Robot Learning Data for Vision-Language Policy","created":"2024-06-28","cited_by_count":52},{"id":"1705.05035","title":"Discrete Sequential Prediction of Continuous Actions for Deep RL","created":"2017-05-14","cited_by_count":51},{"id":"2402.14547","title":"OmniPred: Language Models as Universal Regressors","created":"2024-02-22","cited_by_count":34},{"id":"2004.09805","title":"AMC-Loss: Angular Margin Contrastive Loss for Improved Explainability in Image Classification","created":"2020-04-21","cited_by_count":14},{"id":"2205.12616","title":"Guiding Visual Question Answering with Attention Priors","created":"2022-05-25","cited_by_count":7},{"id":"2310.04691","title":"EMO: Earth Mover Distance Optimization for Auto-Regressive Language Modeling","created":"2023-10-07","cited_by_count":7},{"id":"2402.06512","title":"Multimodal Clinical Trial Outcome Prediction with Large Language Models","created":"2024-02-09","cited_by_count":7},{"id":"2006.14028","title":"Class-Similarity Based Label Smoothing for Confidence Calibration","created":"2020-06-24","cited_by_count":3},{"id":"2410.16212","title":"Comprehensive benchmarking of large language models for RNA secondary structure prediction","created":"2024-10-21","cited_by_count":3},{"id":"2110.05355","title":"Instance-based Label Smoothing For Better Calibrated Classification Networks","created":"2021-10-11","cited_by_count":2}],"next_cursor":null}