{"list":"other","total":69,"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":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"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":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"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":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"1901.05103","title":"DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation","created":"2019-01-16","cited_by_count":2689},{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"1812.03828","title":"Occupancy Networks: Learning 3D Reconstruction in Function Space","created":"2018-12-10","cited_by_count":2041},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"2112.05131","title":"Plenoxels: Radiance Fields without Neural Networks","created":"2021-12-09","cited_by_count":1613},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"2303.11328","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","created":"2023-03-20","cited_by_count":1489},{"id":"2405.12213","title":"Octo: An Open-Source Generalist Robot Policy","created":"2024-05-20","cited_by_count":1484},{"id":"2211.10440","title":"Magic3D: High-Resolution Text-to-3D Content Creation","created":"2022-11-18","cited_by_count":1290},{"id":"2209.07753","title":"Code as Policies: Language Model Programs for Embodied Control","created":"2022-09-16","cited_by_count":1210},{"id":"2207.05608","title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","created":"2022-07-12","cited_by_count":1081},{"id":"2201.07207","title":"Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents","created":"2022-01-18","cited_by_count":1035},{"id":"1612.00603","title":"A Point Set Generation Network for 3D Object Reconstruction from a Single Image","created":"2016-12-02","cited_by_count":979},{"id":"1804.01654","title":"Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images","created":"2018-04-05","cited_by_count":651},{"id":"2209.11302","title":"ProgPrompt: Generating Situated Robot Task Plans using Large Language Models","created":"2022-09-22","cited_by_count":611},{"id":"2212.00774","title":"Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation","created":"2022-12-01","cited_by_count":597},{"id":"1610.07584","title":"Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling","created":"2016-10-24","cited_by_count":558},{"id":"2112.01455","title":"Zero-Shot Text-Guided Object Generation with Dream Fields","created":"2021-12-02","cited_by_count":513},{"id":"2303.12789","title":"Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions","created":"2023-03-22","cited_by_count":484},{"id":"2210.03094","title":"VIMA: General Robot Manipulation with Multimodal Prompts","created":"2022-10-06","cited_by_count":407},{"id":"2109.07547","title":"RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching","created":"2021-09-15","cited_by_count":353},{"id":"2303.12153","title":"Text2Motion: From Natural Language Instructions to Feasible Plans","created":"2023-03-21","cited_by_count":224},{"id":"2307.04721","title":"Large Language Models as General Pattern Machines","created":"2023-07-10","cited_by_count":197},{"id":"2311.00176","title":"ChipNeMo: Domain-Adapted LLMs for Chip Design","created":"2023-10-31","cited_by_count":174},{"id":"1803.08495","title":"Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddings","created":"2018-03-22","cited_by_count":169},{"id":"2209.09874","title":"Open-vocabulary Queryable Scene Representations for Real World Planning","created":"2022-09-20","cited_by_count":160},{"id":"2307.14535","title":"Scaling Up and Distilling Down: Language-Guided Robot Skill Acquisition","created":"2023-07-26","cited_by_count":159},{"id":"2202.08227","title":"Ditto: Building Digital Twins of Articulated Objects from Interaction","created":"2022-02-16","cited_by_count":156},{"id":"2403.03174","title":"MOKA: Open-World Robotic Manipulation through Mark-Based Visual Prompting","created":"2024-03-05","cited_by_count":129},{"id":"1904.11621","title":"Meta-Sim: Learning to Generate Synthetic Datasets","created":"2019-04-25","cited_by_count":128},{"id":"2310.01361","title":"GenSim: Generating Robotic Simulation Tasks via Large Language Models","created":"2023-10-02","cited_by_count":125},{"id":"2206.03429","title":"Generating Long Videos of Dynamic Scenes","created":"2022-06-07","cited_by_count":113},{"id":"1903.03878","title":"Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks","created":"2019-03-09","cited_by_count":107},{"id":"1904.12165","title":"Improved Conditional VRNNs for Video Prediction","created":"2019-04-27","cited_by_count":104},{"id":"1608.05137","title":"IM2CAD","created":"2016-08-18","cited_by_count":78},{"id":"2408.15980","title":"In-Context Imitation Learning via Next-Token Prediction","created":"2024-08-28","cited_by_count":70},{"id":"2402.13232","title":"A Touch, Vision, and Language Dataset for Multimodal Alignment","created":"2024-02-20","cited_by_count":69},{"id":"2302.01295","title":"Ditto in the House: Building Articulation Models of Indoor Scenes through Interactive Perception","created":"2023-02-02","cited_by_count":41},{"id":"2404.07917","title":"DesignQA: A Multimodal Benchmark for Evaluating Large Language Models' Understanding of Engineering Documentation","created":"2024-04-11","cited_by_count":32},{"id":"2406.00144","title":"Query2CAD: Generating CAD models using natural language queries","created":"2024-05-31","cited_by_count":29},{"id":"2007.00350","title":"Adaptive Procedural Task Generation for Hard-Exploration Problems","created":"2020-07-01","cited_by_count":20},{"id":"2309.16909","title":"ASAP: Automated Sequence Planning for Complex Robotic Assembly with Physical Feasibility","created":"2023-09-29","cited_by_count":18},{"id":"2409.14066","title":"KALIE: Fine-Tuning Vision-Language Models for Open-World Manipulation without Robot Data","created":"2024-09-21","cited_by_count":15},{"id":"2304.11018","title":"Robot-Enabled Construction Assembly with Automated Sequence Planning based on ChatGPT: RoboGPT","created":"2023-04-21","cited_by_count":11},{"id":"2210.01340","title":"Safe Self-Supervised Learning in Real of Visuo-Tactile Feedback Policies for Industrial Insertion","created":"2022-10-04","cited_by_count":7},{"id":"2010.08052","title":"A Learning Approach to Robot-Agnostic Force-Guided High Precision Assembly","created":"2020-10-15","cited_by_count":6},{"id":"2211.03977","title":"Assemble Them All: Physics-Based Planning for Generalizable Assembly by Disassembly","created":"2022-11-08","cited_by_count":6},{"id":"2405.08216","title":"Toward Automated Programming for Robotic Assembly Using ChatGPT","created":"2024-05-13","cited_by_count":6},{"id":"2106.13935","title":"Discovering Generalizable Skills via Automated Generation of Diverse Tasks","created":"2021-06-26","cited_by_count":5},{"id":"2111.01391","title":"IPC-GraspSim: Reducing the Sim2Real Gap for Parallel-Jaw Grasping with the Incremental Potential Contact Model","created":"2021-11-02","cited_by_count":4},{"id":"2207.02347","title":"Mechanical Search on Shelves with Efficient Stacking and Destacking of Objects","created":"2022-07-05","cited_by_count":3},{"id":"2211.06134","title":"Active Task Randomization: Learning Robust Skills via Unsupervised Generation of Diverse and Feasible Tasks","created":"2022-11-11","cited_by_count":3},{"id":"2405.09997","title":"Generative Design through Quality-Diversity Data Synthesis and Language Models","created":"2024-05-16","cited_by_count":3}],"next_cursor":null}