{"list":"other","total":67,"rows":[{"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":"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":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"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":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"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":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"1511.02283","title":"Generation and Comprehension of Unambiguous Object Descriptions","created":"2015-11-07","cited_by_count":904},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"1612.03716","title":"COCO-Stuff: Thing and Stuff Classes in Context","created":"2016-12-12","cited_by_count":864},{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776},{"id":"1909.12271","title":"RLBench: The Robot Learning Benchmark & Learning Environment","created":"2019-09-26","cited_by_count":689},{"id":"2308.12952","title":"BridgeData V2: A Dataset for Robot Learning at Scale","created":"2023-08-24","cited_by_count":657},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622},{"id":"2210.04150","title":"Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP","created":"2022-10-09","cited_by_count":565},{"id":"2304.06718","title":"Segment Everything Everywhere All at Once","created":"2023-04-13","cited_by_count":548},{"id":"2307.07635","title":"CoTracker: It is Better to Track Together","created":"2023-07-14","cited_by_count":522},{"id":"2211.11559","title":"Visual Programming: Compositional visual reasoning without training","created":"2022-11-18","cited_by_count":516},{"id":"2409.01652","title":"ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation","created":"2024-09-03","cited_by_count":315},{"id":"2306.17582","title":"ChatGPT for Robotics: Design Principles and Model Abilities","created":"2023-02-20","cited_by_count":299},{"id":"2212.11270","title":"Generalized Decoding for Pixel, Image, and Language","created":"2022-12-21","cited_by_count":294},{"id":"2306.00968","title":"GRES: Generalized Referring Expression Segmentation","created":"2023-06-01","cited_by_count":254},{"id":"2406.10721","title":"RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Robotics","created":"2024-06-15","cited_by_count":251},{"id":"1406.2031","title":"Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts","created":"2014-06-08","cited_by_count":232},{"id":"2312.02228","title":"PixelLM: Pixel Reasoning with Large Multimodal Model","created":"2023-12-04","cited_by_count":222},{"id":"2402.07872","title":"PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs","created":"2024-02-12","cited_by_count":190},{"id":"2307.04767","title":"Semantic-SAM: Segment and Recognize Anything at Any Granularity","created":"2023-07-10","cited_by_count":185},{"id":"2306.15724","title":"REFLECT: Summarizing Robot Experiences for Failure Explanation and Correction","created":"2023-06-27","cited_by_count":175},{"id":"2306.06687","title":"LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark","created":"2023-06-11","cited_by_count":169},{"id":"2301.01795","title":"PACO: Parts and Attributes of Common Objects","created":"2023-01-04","cited_by_count":146},{"id":"2303.07280","title":"Vision-Language Models as Success Detectors","created":"2023-03-13","cited_by_count":142},{"id":"2305.11014","title":"Generalized Planning in PDDL Domains with Pretrained Large Language Models","created":"2023-05-18","cited_by_count":139},{"id":"2406.08545","title":"RVT-2: Learning Precise Manipulation from Few Demonstrations","created":"2024-06-12","cited_by_count":137},{"id":"2410.00371","title":"AHA: A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulation","created":"2024-10-01","cited_by_count":125},{"id":"2403.08248","title":"CoPa: General Robotic Manipulation through Spatial Constraints of Parts with Foundation Models","created":"2024-03-13","cited_by_count":99},{"id":"2406.12030","title":"SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model","created":"2024-06-17","cited_by_count":85},{"id":"2309.06440","title":"LEAP Hand: Low-Cost, Efficient, and Anthropomorphic Hand for Robot Learning","created":"2023-09-12","cited_by_count":79},{"id":"2312.07472","title":"MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active Perception","created":"2023-12-12","cited_by_count":67},{"id":"2311.15383","title":"Visual Programming for Zero-shot Open-Vocabulary 3D Visual Grounding","created":"2023-11-26","cited_by_count":64},{"id":"2411.19939","title":"VLSBench: Unveiling Visual Leakage in Multimodal Safety","created":"2024-11-29","cited_by_count":63},{"id":"2307.00329","title":"DoReMi: Grounding Language Model by Detecting and Recovering from Plan-Execution Misalignment","created":"2023-07-01","cited_by_count":61},{"id":"2402.16117","title":"RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis","created":"2024-02-25","cited_by_count":58},{"id":"2403.12037","title":"MineDreamer: Learning to Follow Instructions via Chain-of-Imagination for Simulated-World Control","created":"2024-03-18","cited_by_count":53},{"id":"2409.14674","title":"RACER: Rich Language-Guided Failure Recovery Policies for Imitation Learning","created":"2024-09-23","cited_by_count":49},{"id":"2303.14100","title":"Errors are Useful Prompts: Instruction Guided Task Programming with Verifier-Assisted Iterative Prompting","created":"2023-03-24","cited_by_count":46},{"id":"2411.18623","title":"Lift3D Foundation Policy: Lifting 2D Large-Scale Pretrained Models for Robust 3D Robotic Manipulation","created":"2024-11-27","cited_by_count":46},{"id":"2410.23004","title":"DexGraspNet 2.0: Learning Generative Dexterous Grasping in Large-scale Synthetic Cluttered Scenes","created":"2024-10-30","cited_by_count":44},{"id":"2402.04764","title":"Code as Reward: Empowering Reinforcement Learning with VLMs","created":"2024-02-07","cited_by_count":39},{"id":"2403.17830","title":"Assessment of Multimodal Large Language Models in Alignment with Human Values","created":"2024-03-26","cited_by_count":36},{"id":"2410.03132","title":"Autoregressive Action Sequence Learning for Robotic Manipulation","created":"2024-10-04","cited_by_count":27},{"id":"2407.10341","title":"Affordance-Guided Reinforcement Learning via Visual Prompting","created":"2024-07-14","cited_by_count":23},{"id":"2409.17143","title":"Attention Prompting on Image for Large Vision-Language Models","created":"2024-09-25","cited_by_count":23},{"id":"2403.19622","title":"RH20T-P: A Primitive-Level Robotic Dataset Towards Composable Generalization Agents","created":"2024-03-28","cited_by_count":20},{"id":"2405.19783","title":"Instruction-Guided Visual Masking","created":"2024-05-30","cited_by_count":17},{"id":"2406.00430","title":"Evaluating Uncertainty-based Failure Detection for Closed-Loop LLM Planners","created":"2024-06-01","cited_by_count":15},{"id":"2406.03474","title":"AD-H: Language-guided Autonomous Driving with Hierarchical Agents","created":"2024-06-05","cited_by_count":15},{"id":"2209.05255","title":"A Causal-based Approach to Explain, Predict and Prevent Failures in Robotic Tasks","created":"2022-09-12","cited_by_count":11},{"id":"2403.13352","title":"AGFSync: Leveraging AI-Generated Feedback for Preference Optimization in Text-to-Image Generation","created":"2024-03-20","cited_by_count":9},{"id":"2411.18276","title":"GAPartManip: A Large-scale Part-centric Dataset for Material-Agnostic Articulated Object Manipulation","created":"2024-11-27","cited_by_count":5}],"next_cursor":null}