{"list":"other","total":64,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"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":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2209.07753","title":"Code as Policies: Language Model Programs for Embodied Control","created":"2022-09-16","cited_by_count":1210},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"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":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"2401.12168","title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities","created":"2024-01-22","cited_by_count":706},{"id":"2309.17421","title":"The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)","created":"2023-09-29","cited_by_count":681},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622},{"id":"2209.11302","title":"ProgPrompt: Generating Situated Robot Task Plans using Large Language Models","created":"2022-09-22","cited_by_count":611},{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513},{"id":"2304.11477","title":"LLM+P: Empowering Large Language Models with Optimal Planning Proficiency","created":"2023-04-22","cited_by_count":501},{"id":"1704.06888","title":"Time-Contrastive Networks: Self-Supervised Learning from Video","created":"2017-04-23","cited_by_count":459},{"id":"2207.04429","title":"LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action","created":"2022-07-10","cited_by_count":439},{"id":"2302.01560","title":"Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents","created":"2023-02-03","cited_by_count":398},{"id":"2210.00030","title":"VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training","created":"2022-09-30","cited_by_count":395},{"id":"2409.01652","title":"ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation","created":"2024-09-03","cited_by_count":315},{"id":"2306.08647","title":"Language to Rewards for Robotic Skill Synthesis","created":"2023-06-14","cited_by_count":312},{"id":"2202.07925","title":"ActionFormer: Localizing Moments of Actions with Transformers","created":"2022-02-16","cited_by_count":311},{"id":"2112.04478","title":"Prompting Visual-Language Models for Efficient Video Understanding","created":"2021-12-08","cited_by_count":310},{"id":"2312.05251","title":"Reconstructing Hands in 3D with Transformers","created":"2023-12-08","cited_by_count":306},{"id":"1705.02953","title":"Temporal Segment Networks for Action Recognition in Videos","created":"2017-05-08","cited_by_count":279},{"id":"1806.11230","title":"Human Action Recognition and Prediction: A Survey","created":"2018-06-28","cited_by_count":227},{"id":"2304.08488","title":"Affordances from Human Videos as a Versatile Representation for Robotics","created":"2023-04-17","cited_by_count":226},{"id":"2303.12153","title":"Text2Motion: From Natural Language Instructions to Feasible Plans","created":"2023-03-21","cited_by_count":224},{"id":"2302.12422","title":"MimicPlay: Long-Horizon Imitation Learning by Watching Human Play","created":"2023-02-24","cited_by_count":223},{"id":"2312.07843","title":"Foundation Models in Robotics: Applications, Challenges, and the Future","created":"2023-12-13","cited_by_count":216},{"id":"2401.00025","title":"Any-point Trajectory Modeling for Policy Learning","created":"2023-12-28","cited_by_count":215},{"id":"2402.07872","title":"PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs","created":"2024-02-12","cited_by_count":190},{"id":"1707.03374","title":"Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translation","created":"2017-07-11","cited_by_count":167},{"id":"1703.07814","title":"R-C3D: Region Convolutional 3D Network for Temporal Activity Detection","created":"2017-03-22","cited_by_count":161},{"id":"2207.09450","title":"Human-to-Robot Imitation in the Wild","created":"2022-07-19","cited_by_count":161},{"id":"2305.11014","title":"Generalized Planning in PDDL Domains with Pretrained Large Language Models","created":"2023-05-18","cited_by_count":139},{"id":"2311.01977","title":"RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketches","created":"2023-11-03","cited_by_count":133},{"id":"2103.16817","title":"Learning Generalizable Robotic Reward Functions from \"In-The-Wild\" Human Videos","created":"2021-03-31","cited_by_count":119},{"id":"2106.03911","title":"XIRL: Cross-embodiment Inverse Reinforcement Learning","created":"2021-06-07","cited_by_count":107},{"id":"2212.04498","title":"VideoDex: Learning Dexterity from Internet Videos","created":"2022-12-08","cited_by_count":106},{"id":"1912.04443","title":"AVID: Learning Multi-Stage Tasks via Pixel-Level Translation of Human Videos","created":"2019-12-10","cited_by_count":105},{"id":"2312.08782","title":"Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis","created":"2023-12-14","cited_by_count":103},{"id":"1907.01172","title":"Procedure Planning in Instructional Videos","created":"2019-07-02","cited_by_count":92},{"id":"2101.07241","title":"Learning by Watching: Physical Imitation of Manipulation Skills from Human Videos","created":"2021-01-18","cited_by_count":87},{"id":"2011.06507","title":"Reinforcement Learning with Videos: Combining Offline Observations with Interaction","created":"2020-11-12","cited_by_count":82},{"id":"2201.12716","title":"You Only Demonstrate Once: Category-Level Manipulation from Single Visual Demonstration","created":"2022-01-30","cited_by_count":81},{"id":"2307.09955","title":"XSkill: Cross Embodiment Skill Discovery","created":"2023-07-19","cited_by_count":75},{"id":"1911.09676","title":"Third-Person Visual Imitation Learning via Decoupled Hierarchical Controller","created":"2019-11-21","cited_by_count":73},{"id":"2407.07775","title":"Mobility VLA: Multimodal Instruction Navigation with Long-Context VLMs and Topological Graphs","created":"2024-07-10","cited_by_count":73},{"id":"2204.11134","title":"Can Foundation Models Perform Zero-Shot Task Specification For Robot Manipulation?","created":"2022-04-23","cited_by_count":70},{"id":"1612.06699","title":"Unsupervised Perceptual Rewards for Imitation Learning","created":"2016-12-20","cited_by_count":65},{"id":"1807.03480","title":"Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstration","created":"2018-07-10","cited_by_count":61},{"id":"2010.09034","title":"Model-Based Inverse Reinforcement Learning from Visual Demonstrations","created":"2020-10-18","cited_by_count":52},{"id":"2312.00775","title":"Towards Generalizable Zero-Shot Manipulation via Translating Human Interaction Plans","created":"2023-12-01","cited_by_count":52},{"id":"2403.12943","title":"Vid2Robot: End-to-end Video-conditioned Policy Learning with Cross-Attention Transformers","created":"2024-03-19","cited_by_count":52},{"id":"2405.20321","title":"Vision-based Manipulation from Single Human Video with Open-World Object Graphs","created":"2024-05-30","cited_by_count":50},{"id":"2207.14299","title":"Graph Inverse Reinforcement Learning from Diverse Videos","created":"2022-07-28","cited_by_count":46},{"id":"1912.12773","title":"Learning Predictive Models From Observation and Interaction","created":"2019-12-30","cited_by_count":41},{"id":"2403.02709","title":"RT-Sketch: Goal-Conditioned Imitation Learning from Hand-Drawn Sketches","created":"2024-03-05","cited_by_count":41},{"id":"1612.07796","title":"First-Person Activity Forecasting with Online Inverse Reinforcement Learning","created":"2016-12-22","cited_by_count":40},{"id":"2407.12957","title":"R+X: Retrieval and Execution from Everyday Human Videos","created":"2024-07-17","cited_by_count":38},{"id":"1904.06539","title":"HAKE: Human Activity Knowledge Engine","created":"2019-04-13","cited_by_count":32},{"id":"2402.11450","title":"Learning to Learn Faster from Human Feedback with Language Model Predictive Control","created":"2024-02-18","cited_by_count":26},{"id":"1905.07861","title":"Perceptual Values from Observation","created":"2019-05-20","cited_by_count":11}],"next_cursor":null}