{"list":"other","total":57,"rows":[{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2304.13705","title":"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware","created":"2023-04-23","cited_by_count":1568},{"id":"2305.11206","title":"LIMA: Less Is More for Alignment","created":"2023-05-18","cited_by_count":1100},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"1803.04189","title":"Noise2Noise: Learning Image Restoration without Clean Data","created":"2018-03-12","cited_by_count":533},{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532},{"id":"2202.02005","title":"BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning","created":"2022-02-04","cited_by_count":523},{"id":"2307.07635","title":"CoTracker: It is Better to Track Together","created":"2023-07-14","cited_by_count":522},{"id":"2306.03881","title":"Emergent Correspondence from Image Diffusion","created":"2023-06-06","cited_by_count":446},{"id":"2312.05251","title":"Reconstructing Hands in 3D with Transformers","created":"2023-12-08","cited_by_count":306},{"id":"2309.15807","title":"Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack","created":"2023-09-27","cited_by_count":279},{"id":"2309.11235","title":"OpenChat: Advancing Open-source Language Models with Mixed-Quality Data","created":"2023-09-20","cited_by_count":252},{"id":"2302.12422","title":"MimicPlay: Long-Horizon Imitation Learning by Watching Human Play","created":"2023-02-24","cited_by_count":223},{"id":"2207.09450","title":"Human-to-Robot Imitation in the Wild","created":"2022-07-19","cited_by_count":161},{"id":"2402.00530","title":"Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning","created":"2024-02-01","cited_by_count":138},{"id":"2407.15208","title":"Flow as the Cross-Domain Manipulation Interface","created":"2024-07-21","cited_by_count":132},{"id":"2103.16817","title":"Learning Generalizable Robotic Reward Functions from \"In-The-Wild\" Human Videos","created":"2021-03-31","cited_by_count":119},{"id":"2305.19256","title":"Ambient Diffusion: Learning Clean Distributions from Corrupted Data","created":"2023-05-30","cited_by_count":111},{"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":"2202.10448","title":"Robotic Telekinesis: Learning a Robotic Hand Imitator by Watching Humans on Youtube","created":"2022-02-21","cited_by_count":82},{"id":"2203.13251","title":"Dexterous Imitation Made Easy: A Learning-Based Framework for Efficient Dexterous Manipulation","created":"2022-03-24","cited_by_count":78},{"id":"2307.09955","title":"XSkill: Cross Embodiment Skill Discovery","created":"2023-07-19","cited_by_count":75},{"id":"2503.00779","title":"Phantom: Training Robots Without Robots Using Only Human Videos","created":"2025-03-02","cited_by_count":70},{"id":"2410.11792","title":"OKAMI: Teaching Humanoid Robots Manipulation Skills through Single Video Imitation","created":"2024-10-15","cited_by_count":67},{"id":"2501.06994","title":"Motion Tracks: A Unified Representation for Human-Robot Transfer in Few-Shot Imitation Learning","created":"2025-01-13","cited_by_count":59},{"id":"2302.09057","title":"Consistent Diffusion Models: Mitigating Sampling Drift by Learning to be Consistent","created":"2023-02-17","cited_by_count":58},{"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":"2302.02011","title":"Zero-Shot Robot Manipulation from Passive Human Videos","created":"2023-02-03","cited_by_count":51},{"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":"2408.14037","title":"Re-Mix: Optimizing Data Mixtures for Large Scale Imitation Learning","created":"2024-08-26","cited_by_count":47},{"id":"2502.20391","title":"Point Policy: Unifying Observations and Actions with Key Points for Robot Manipulation","created":"2025-02-27","cited_by_count":47},{"id":"2207.14299","title":"Graph Inverse Reinforcement Learning from Diverse Videos","created":"2022-07-28","cited_by_count":46},{"id":"2404.10177","title":"Consistent Diffusion Meets Tweedie: Training Exact Ambient Diffusion Models with Noisy Data","created":"2024-03-20","cited_by_count":44},{"id":"1907.05518","title":"Graph-Structured Visual Imitation","created":"2019-07-11","cited_by_count":43},{"id":"2508.09976","title":"Masquerade: Learning from In-the-wild Human Videos using Data-Editing","created":"2025-08-13","cited_by_count":43},{"id":"1912.12773","title":"Learning Predictive Models From Observation and Interaction","created":"2019-12-30","cited_by_count":41},{"id":"2411.12633","title":"Instant Policy: In-Context Imitation Learning via Graph Diffusion","created":"2024-11-19","cited_by_count":39},{"id":"2505.07813","title":"DexWild: Dexterous Human Interactions for In-the-Wild Robot Policies","created":"2025-05-12","cited_by_count":38},{"id":"2207.05053","title":"Learning Continuous Grasping Function with a Dexterous Hand from Human Demonstrations","created":"2022-07-11","cited_by_count":34},{"id":"2504.12609","title":"Crossing the Human-Robot Embodiment Gap with Sim-to-Real RL using One Human Demonstration","created":"2025-04-17","cited_by_count":34},{"id":"2505.20290","title":"EgoZero: Robot Learning from Smart Glasses","created":"2025-05-26","cited_by_count":33},{"id":"2404.14735","title":"Rank2Reward: Learning Shaped Reward Functions from Passive Video","created":"2024-04-23","cited_by_count":32},{"id":"2503.23877","title":"ZeroMimic: Distilling Robotic Manipulation Skills from Web Videos","created":"2025-03-31","cited_by_count":32},{"id":"2505.07096","title":"X-Sim: Cross-Embodiment Learning via Real-to-Sim-to-Real","created":"2025-05-11","cited_by_count":28},{"id":"2506.19121","title":"CUPID: Curating Data your Robot Loves with Influence Functions","created":"2025-06-23","cited_by_count":23},{"id":"2310.12077","title":"One-Shot Imitation Learning: A Pose Estimation Perspective","created":"2023-10-18","cited_by_count":21},{"id":"2509.09769","title":"MimicDroid: In-Context Learning for Humanoid Robot Manipulation from Human Play Videos","created":"2025-09-11","cited_by_count":20},{"id":"2411.02780","title":"How much is a noisy image worth? Data Scaling Laws for Ambient Diffusion","created":"2024-11-05","cited_by_count":18},{"id":"2503.03707","title":"Curating Demonstrations using Online Experience","created":"2025-03-05","cited_by_count":18},{"id":"2506.10038","title":"Ambient Diffusion Omni: Training Good Models with Bad Data","created":"2025-06-10","cited_by_count":18},{"id":"2503.00774","title":"Shadow: Leveraging Segmentation Masks for Cross-Embodiment Policy Transfer","created":"2025-03-02","cited_by_count":14},{"id":"2508.20085","title":"HERMES: Human-to-Robot Embodied Learning from Multi-Source Motion Data for Mobile Dexterous Manipulation","created":"2025-08-27","cited_by_count":14},{"id":"2409.06615","title":"One-Shot Imitation under Mismatched Execution","created":"2024-09-10","cited_by_count":12},{"id":"2502.05397","title":"Imitation Learning from a Single Temporally Misaligned Video","created":"2025-02-08","cited_by_count":7},{"id":"2504.03478","title":"Probabilistic Machine Learning for Noisy Labels in Earth Observation","created":"2025-04-04","cited_by_count":6}],"next_cursor":null}