{"list":"other","total":61,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"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":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"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":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"1902.09630","title":"Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression","created":"2019-02-25","cited_by_count":1368},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"2106.12052","title":"Volume Rendering of Neural Implicit Surfaces","created":"2021-06-22","cited_by_count":996},{"id":"2212.08751","title":"Point-E: A System for Generating 3D Point Clouds from Complex Prompts","created":"2022-12-16","cited_by_count":699},{"id":"1804.10959","title":"Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates","created":"2018-04-29","cited_by_count":639},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"id":"2302.14045","title":"Language Is Not All You Need: Aligning Perception with Language Models","created":"2023-02-27","cited_by_count":543},{"id":"2306.14795","title":"MotionGPT: Human Motion as a Foreign Language","created":"2023-06-26","cited_by_count":527},{"id":"2104.03670","title":"3D Shape Generation and Completion through Point-Voxel Diffusion","created":"2021-04-08","cited_by_count":516},{"id":"2208.10442","title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","created":"2022-08-22","cited_by_count":511},{"id":"2301.11445","title":"3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models","created":"2023-01-26","cited_by_count":458},{"id":"2206.08916","title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","created":"2022-06-17","cited_by_count":421},{"id":"2106.13043","title":"AudioCLIP: Extending CLIP to Image, Text and Audio","created":"2021-06-24","cited_by_count":339},{"id":"1905.10711","title":"DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction","created":"2019-05-26","cited_by_count":333},{"id":"2212.04493","title":"SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generation","created":"2022-12-08","cited_by_count":288},{"id":"2203.13333","title":"CLIP-Mesh: Generating textured meshes from text using pretrained image-text models","created":"2022-03-24","cited_by_count":281},{"id":"2311.15475","title":"MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers","created":"2023-11-27","cited_by_count":259},{"id":"2110.02624","title":"CLIP-Forge: Towards Zero-Shot Text-to-Shape Generation","created":"2021-10-06","cited_by_count":254},{"id":"2306.17115","title":"Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation","created":"2023-06-29","cited_by_count":228},{"id":"2203.09516","title":"AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generation","created":"2022-03-17","cited_by_count":208},{"id":"2207.04901","title":"Exploring Length Generalization in Large Language Models","created":"2022-07-11","cited_by_count":206},{"id":"2309.00615","title":"Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following","created":"2023-09-01","cited_by_count":194},{"id":"1803.08495","title":"Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddings","created":"2018-03-22","cited_by_count":169},{"id":"1901.11153","title":"Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Images","created":"2019-01-31","cited_by_count":164},{"id":"2303.12048","title":"Vox-E: Text-guided Voxel Editing of 3D Objects","created":"2023-03-21","cited_by_count":115},{"id":"2105.09996","title":"VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding","created":"2021-05-20","cited_by_count":102},{"id":"2302.10668","title":"$PC^2$: Projection-Conditioned Point Cloud Diffusion for Single-Image 3D Reconstruction","created":"2023-02-21","cited_by_count":84},{"id":"2112.01988","title":"ROCA: Robust CAD Model Retrieval and Alignment from a Single Image","created":"2021-12-03","cited_by_count":67},{"id":"2207.09446","title":"ShapeCrafter: A Recursive Text-Conditioned 3D Shape Generation Model","created":"2022-07-19","cited_by_count":62},{"id":"2003.07717","title":"Multimodal Shape Completion via Conditional Generative Adversarial Networks","created":"2020-03-17","cited_by_count":61},{"id":"2210.01820","title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","created":"2022-10-04","cited_by_count":47},{"id":"2010.07174","title":"The EOS Decision and Length Extrapolation","created":"2020-10-14","cited_by_count":46},{"id":"2206.04382","title":"CLIP-Actor: Text-Driven Recommendation and Stylization for Animating Human Meshes","created":"2022-06-09","cited_by_count":41},{"id":"2111.12480","title":"Octree Transformer: Autoregressive 3D Shape Generation on Hierarchically Structured Sequences","created":"2021-11-24","cited_by_count":39},{"id":"2108.09936","title":"Voxel-based Network for Shape Completion by Leveraging Edge Generation","created":"2021-08-23","cited_by_count":32},{"id":"1908.00120","title":"ShapeCaptioner: Generative Caption Network for 3D Shapes by Learning a Mapping from Parts Detected in Multiple Views to Sentences","created":"2019-07-31","cited_by_count":30},{"id":"2204.09866","title":"Pixel2Mesh++: 3D Mesh Generation and Refinement from Multi-View Images","created":"2022-04-21","cited_by_count":21},{"id":"2210.11170","title":"Coordinates Are NOT Lonely -- Codebook Prior Helps Implicit Neural 3D Representations","created":"2022-10-20","cited_by_count":13},{"id":"2103.15813","title":"PixelTransformer: Sample Conditioned Signal Generation","created":"2021-03-29","cited_by_count":12},{"id":"2306.10830","title":"3D VR Sketch Guided 3D Shape Prototyping and Exploration","created":"2023-06-19","cited_by_count":12},{"id":"2301.07236","title":"Effective End-to-End Vision Language Pretraining with Semantic Visual Loss","created":"2023-01-18","cited_by_count":10},{"id":"2211.08702","title":"PointInverter: Point Cloud Reconstruction and Editing via a Generative Model with Shape Priors","created":"2022-11-16","cited_by_count":5}],"next_cursor":null}