{"list":"other","total":74,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2112.09332","title":"WebGPT: Browser-assisted question-answering with human feedback","created":"2021-12-17","cited_by_count":1745},{"id":"2309.07864","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","created":"2023-09-14","cited_by_count":1439},{"id":"2303.17760","title":"CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society","created":"2023-03-31","cited_by_count":1395},{"id":"2303.17580","title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","created":"2023-03-30","cited_by_count":1190},{"id":"1802.01436","title":"Variational image compression with a scale hyperprior","created":"2018-02-01","cited_by_count":935},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"2204.07705","title":"Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks","created":"2022-04-16","cited_by_count":868},{"id":"1908.03265","title":"On the Variance of the Adaptive Learning Rate and Beyond","created":"2019-08-08","cited_by_count":772},{"id":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719},{"id":"1611.01704","title":"End-to-end Optimized Image Compression","created":"2016-11-05","cited_by_count":696},{"id":"1809.02736","title":"Joint Autoregressive and Hierarchical Priors for Learned Image Compression","created":"2018-09-08","cited_by_count":664},{"id":"2001.01568","title":"Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules","created":"2020-01-06","cited_by_count":590},{"id":"2110.15943","title":"MetaICL: Learning to Learn In Context","created":"2021-10-29","cited_by_count":454},{"id":"2304.09842","title":"Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models","created":"2023-04-19","cited_by_count":356},{"id":"2006.09965","title":"High-Fidelity Generative Image Compression","created":"2020-06-17","cited_by_count":338},{"id":"2203.10886","title":"ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding","created":"2022-03-21","cited_by_count":301},{"id":"1703.00395","title":"Lossy Image Compression with Compressive Autoencoders","created":"2017-03-01","cited_by_count":294},{"id":"2305.15021","title":"EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought","created":"2023-05-24","cited_by_count":279},{"id":"2007.08739","title":"Channel-wise Autoregressive Entropy Models for Learned Image Compression","created":"2020-07-17","cited_by_count":264},{"id":"2305.18752","title":"GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction","created":"2023-05-30","cited_by_count":248},{"id":"2401.11708","title":"Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs","created":"2024-01-22","cited_by_count":224},{"id":"2303.14978","title":"Learned Image Compression with Mixed Transformer-CNN Architectures","created":"2023-03-27","cited_by_count":211},{"id":"2212.10450","title":"Is GPT-3 a Good Data Annotator?","created":"2022-12-20","cited_by_count":208},{"id":"2311.05437","title":"LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents","created":"2023-11-09","cited_by_count":193},{"id":"1511.06085","title":"Variable Rate Image Compression with Recurrent Neural Networks","created":"2015-11-19","cited_by_count":173},{"id":"2209.06950","title":"Lossy Image Compression with Conditional Diffusion Models","created":"2022-09-14","cited_by_count":170},{"id":"2304.04675","title":"Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis","created":"2023-04-10","cited_by_count":160},{"id":"1704.00648","title":"Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations","created":"2017-04-03","cited_by_count":152},{"id":"2203.08450","title":"The Devil Is in the Details: Window-based Attention for Image Compression","created":"2022-03-16","cited_by_count":147},{"id":"2007.03034","title":"Nonlinear Transform Coding","created":"2020-07-06","cited_by_count":136},{"id":"2407.05600","title":"GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editing","created":"2024-07-08","cited_by_count":133},{"id":"2304.05332","title":"Emergent autonomous scientific research capabilities of large language models","created":"2023-04-11","cited_by_count":132},{"id":"1909.04802","title":"Variable Rate Deep Image Compression With a Conditional Autoencoder","created":"2019-09-11","cited_by_count":114},{"id":"2203.03041","title":"Highly Accurate Dichotomous Image Segmentation","created":"2022-03-06","cited_by_count":110},{"id":"2310.00656","title":"LEGO-Prover: Neural Theorem Proving with Growing Libraries","created":"2023-10-01","cited_by_count":109},{"id":"2310.10325","title":"Towards image compression with perfect realism at ultra-low bitrates","created":"2023-10-16","cited_by_count":103},{"id":"2301.11189","title":"Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Models","created":"2023-01-26","cited_by_count":94},{"id":"2003.02012","title":"Asymmetric Gained Deep Image Compression With Continuous Rate Adaptation","created":"2020-03-04","cited_by_count":85},{"id":"2006.04240","title":"Improving Inference for Neural Image Compression","created":"2020-06-07","cited_by_count":83},{"id":"2212.13824","title":"Multi-Realism Image Compression with a Conditional Generator","created":"2022-12-28","cited_by_count":80},{"id":"2011.09704","title":"Causal Contextual Prediction for Learned Image Compression","created":"2020-11-19","cited_by_count":73},{"id":"2310.08588","title":"Octopus: Embodied Vision-Language Programmer from Environmental Feedback","created":"2023-10-12","cited_by_count":73},{"id":"2108.09551","title":"Variable-Rate Deep Image Compression through Spatially-Adaptive Feature Transform","created":"2021-08-21","cited_by_count":58},{"id":"2310.16387","title":"Frequency-Aware Transformer for Learned Image Compression","created":"2023-10-25","cited_by_count":58},{"id":"2104.05168","title":"Soft then Hard: Rethinking the Quantization in Neural Image Compression","created":"2021-04-12","cited_by_count":51},{"id":"2302.00871","title":"Using In-Context Learning to Improve Dialogue Safety","created":"2023-02-02","cited_by_count":42},{"id":"2301.05489","title":"A Residual Diffusion Model for High Perceptual Quality Codec Augmentation","created":"2023-01-13","cited_by_count":35},{"id":"2306.05085","title":"TransTIC: Transferring Transformer-based Image Compression from Human Perception to Machine Perception","created":"2023-06-08","cited_by_count":32},{"id":"2207.01932","title":"Image Coding for Machines with Omnipotent Feature Learning","created":"2022-07-05","cited_by_count":31},{"id":"2012.09550","title":"Learned Block-based Hybrid Image Compression","created":"2020-12-17","cited_by_count":30},{"id":"2407.09853","title":"Image Compression for Machine and Human Vision with Spatial-Frequency Adaptation","created":"2024-07-13","cited_by_count":26},{"id":"2305.08804","title":"Exploring In-Context Learning Capabilities of Foundation Models for Generating Knowledge Graphs from Text","created":"2023-05-15","cited_by_count":19},{"id":"2405.16817","title":"Controlling Rate, Distortion, and Realism: Towards a Single Comprehensive Neural Image Compression Model","created":"2024-05-27","cited_by_count":17},{"id":"2305.16025","title":"NVTC: Nonlinear Vector Transform Coding","created":"2023-05-25","cited_by_count":14},{"id":"2309.03244","title":"EGIC: Enhanced Low-Bit-Rate Generative Image Compression Guided by Semantic Segmentation","created":"2023-09-06","cited_by_count":14},{"id":"2109.09280","title":"Interpolation variable rate image compression","created":"2021-09-20","cited_by_count":12},{"id":"2305.02586","title":"Semantically Structured Image Compression via Irregular Group-Based Decoupling","created":"2023-05-04","cited_by_count":12},{"id":"2404.01342","title":"DiffAgent: Fast and Accurate Text-to-Image API Selection with Large Language Model","created":"2024-03-31","cited_by_count":12},{"id":"2407.11700","title":"Rate-Distortion-Cognition Controllable Versatile Neural Image Compression","created":"2024-07-16","cited_by_count":11},{"id":"2305.10807","title":"Transformer-based Variable-rate Image Compression with Region-of-interest Control","created":"2023-05-18","cited_by_count":7}],"next_cursor":null}