{"list":"other","total":62,"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":"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":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"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":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"1901.05103","title":"DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation","created":"2019-01-16","cited_by_count":2689},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"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":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162},{"id":"2405.04434","title":"DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model","created":"2024-05-07","cited_by_count":1135},{"id":"2403.17888","title":"2D Gaussian Splatting for Geometrically Accurate Radiance Fields","created":"2024-03-26","cited_by_count":1076},{"id":"2305.14233","title":"Enhancing Chat Language Models by Scaling High-quality Instructional Conversations","created":"2023-05-23","cited_by_count":839},{"id":"2307.05663","title":"Objaverse-XL: A Universe of 10M+ 3D Objects","created":"2023-07-11","cited_by_count":774},{"id":"2401.02954","title":"DeepSeek LLM: Scaling Open-Source Language Models with Longtermism","created":"2024-01-05","cited_by_count":642},{"id":"2305.11000","title":"SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities","created":"2023-05-18","cited_by_count":529},{"id":"2305.02463","title":"Shap-E: Generating Conditional 3D Implicit Functions","created":"2023-05-03","cited_by_count":385},{"id":"2106.13043","title":"AudioCLIP: Extending CLIP to Image, Text and Audio","created":"2021-06-24","cited_by_count":339},{"id":"2308.16911","title":"PointLLM: Empowering Large Language Models to Understand Point Clouds","created":"2023-08-31","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":"2002.10880","title":"PolyGen: An Autoregressive Generative Model of 3D Meshes","created":"2020-02-23","cited_by_count":269},{"id":"2107.02137","title":"ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation","created":"2021-07-05","cited_by_count":260},{"id":"2311.15475","title":"MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers","created":"2023-11-27","cited_by_count":259},{"id":"2307.08177","title":"Using an LLM to Help With Code Understanding","created":"2023-07-17","cited_by_count":228},{"id":"2212.01206","title":"DiffRF: Rendering-Guided 3D Radiance Field Diffusion","created":"2022-12-02","cited_by_count":204},{"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":"2303.05371","title":"3DGen: Triplane Latent Diffusion for Textured Mesh Generation","created":"2023-03-09","cited_by_count":183},{"id":"2403.11401","title":"Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning","created":"2024-03-18","cited_by_count":175},{"id":"2303.17015","title":"HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusion","created":"2023-03-29","cited_by_count":152},{"id":"2406.10163","title":"MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers","created":"2024-06-14","cited_by_count":144},{"id":"2405.10370","title":"Grounded 3D-LLM with Referent Tokens","created":"2024-05-16","cited_by_count":115},{"id":"2408.02555","title":"MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization","created":"2024-08-05","cited_by_count":104},{"id":"2405.20853","title":"MeshXL: Neural Coordinate Field for Generative 3D Foundation Models","created":"2024-05-31","cited_by_count":103},{"id":"2411.07184","title":"SAMPart3D: Segment Any Part in 3D Objects","created":"2024-11-11","cited_by_count":97},{"id":"2411.09595","title":"LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models","created":"2024-11-14","cited_by_count":91},{"id":"2412.09548","title":"Meshtron: High-Fidelity, Artist-Like 3D Mesh Generation at Scale","created":"2024-12-12","cited_by_count":89},{"id":"2308.11276","title":"Music Understanding LLaMA: Advancing Text-to-Music Generation with Question Answering and Captioning","created":"2023-08-22","cited_by_count":77},{"id":"2411.07025","title":"Scaling Mesh Generation via Compressive Tokenization","created":"2024-11-11","cited_by_count":73},{"id":"2312.11417","title":"PolyDiff: Generating 3D Polygonal Meshes with Diffusion Models","created":"2023-12-18","cited_by_count":66},{"id":"2308.15930","title":"LLaSM: Large Language and Speech Model","created":"2023-08-30","cited_by_count":58},{"id":"1811.10464","title":"Scan2Mesh: From Unstructured Range Scans to 3D Meshes","created":"2018-11-26","cited_by_count":51},{"id":"2405.16890","title":"PivotMesh: Generic 3D Mesh Generation via Pivot Vertices Guidance","created":"2024-05-27","cited_by_count":50},{"id":"2404.18202","title":"WorldGPT: Empowering LLM as Multimodal World Model","created":"2024-04-28","cited_by_count":42},{"id":"2311.17618","title":"ShapeGPT: 3D Shape Generation with A Unified Multi-modal Language Model","created":"2023-11-29","cited_by_count":39},{"id":"2411.16602","title":"Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion Models","created":"2024-11-25","cited_by_count":38},{"id":"2408.08313","title":"Can Large Language Models Understand Symbolic Graphics Programs?","created":"2024-08-15","cited_by_count":35},{"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":"1811.02745","title":"Y^2Seq2Seq: Cross-Modal Representation Learning for 3D Shape and Text by Joint Reconstruction and Prediction of View and Word Sequences","created":"2018-11-07","cited_by_count":27},{"id":"2407.06842","title":"Chat-Edit-3D: Interactive 3D Scene Editing via Text Prompts","created":"2024-07-09","cited_by_count":19},{"id":"2312.00249","title":"Acoustic Prompt Tuning: Empowering Large Language Models with Audition Capabilities","created":"2023-11-30","cited_by_count":10}],"next_cursor":null}