{"total":74,"rows":[{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681,"area":null},{"id":"2103.04918","title":"A Survey of Embodied AI: From Simulators to Research Tasks","created":"2021-03-08","cited_by_count":261,"area":null},{"id":"2507.01925","title":"A Survey on Vision-Language-Action Models: An Action Tokenization Perspective","created":"2025-07-02","cited_by_count":96,"area":"vla"},{"id":"2103.14025","title":"The ThreeDWorld Transport Challenge: A Visually Guided Task-and-Motion Planning Benchmark for Physically Realistic Embodied AI","created":"2021-03-25","cited_by_count":65,"area":null},{"id":"2312.01072","title":"A Survey of Temporal Credit Assignment in Deep Reinforcement Learning","created":"2023-12-02","cited_by_count":59,"area":null},{"id":"2104.04258","title":"Counter-Strike Deathmatch with Large-Scale Behavioural Cloning","created":"2021-04-09","cited_by_count":50,"area":"offlinerl"},{"id":"2312.10136","title":"Gradient-based Parameter Selection for Efficient Fine-Tuning","created":"2023-12-15","cited_by_count":40,"area":null},{"id":"2110.10067","title":"CORA: Benchmarks, Baselines, and Metrics as a Platform for Continual Reinforcement Learning Agents","created":"2021-10-19","cited_by_count":38,"area":null},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36,"area":null},{"id":"2112.09605","title":"Autonomous Reinforcement Learning: Formalism and Benchmarking","created":"2021-12-17","cited_by_count":33,"area":null},{"id":"2106.03805","title":"3DB: A Framework for Debugging Computer Vision Models","created":"2021-06-07","cited_by_count":31,"area":null},{"id":"2106.13948","title":"Core Challenges in Embodied Vision-Language Planning","created":"2021-06-26","cited_by_count":30,"area":null},{"id":"2604.07429","title":"GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents","created":"2026-04-08","cited_by_count":28,"area":"mllm"},{"id":"2402.02242","title":"Parameter-Efficient Fine-Tuning for Pre-Trained Vision Models: A Survey and Benchmark","created":"2024-02-03","cited_by_count":23,"area":null},{"id":"2109.03351","title":"Capturing the objects of vision with neural networks","created":"2021-09-07","cited_by_count":21,"area":null},{"id":"2309.08513","title":"SCT: A Simple Baseline for Parameter-Efficient Fine-Tuning via Salient Channels","created":"2023-09-15","cited_by_count":20,"area":null},{"id":"2203.06369","title":"The Health Gym: Synthetic Health-Related Datasets for the Development of Reinforcement Learning Algorithms","created":"2022-03-12","cited_by_count":19,"area":null},{"id":"2506.21872","title":"A Survey of Continual Reinforcement Learning","created":"2025-06-27","cited_by_count":18,"area":"deeprl"},{"id":"2107.06011","title":"Teaching Agents how to Map: Spatial Reasoning for Multi-Object Navigation","created":"2021-07-13","cited_by_count":17,"area":null},{"id":"2210.13417","title":"Avalon: A Benchmark for RL Generalization Using Procedurally Generated Worlds","created":"2022-10-24","cited_by_count":17,"area":null},{"id":"2403.09192","title":"PYRA: Parallel Yielding Re-Activation for Training-Inference Efficient Task Adaptation","created":"2024-03-14","cited_by_count":17,"area":null},{"id":"2103.08255","title":"Sample-efficient Reinforcement Learning Representation Learning with Curiosity Contrastive Forward Dynamics Model","created":"2021-03-15","cited_by_count":16,"area":null},{"id":"2304.13269","title":"Games for Artificial Intelligence Research: A Review and Perspectives","created":"2023-04-26","cited_by_count":14,"area":null},{"id":"2208.03374","title":"Learning to Generalize with Object-centric Agents in the Open World Survival Game Crafter","created":"2022-08-05","cited_by_count":13,"area":null},{"id":"2407.08590","title":"A Review of Nine Physics Engines for Reinforcement Learning Research","created":"2024-07-11","cited_by_count":12,"area":"deeprl"},{"id":"2309.03081","title":"ORL-AUDITOR: Dataset Auditing in Offline Deep Reinforcement Learning","created":"2023-09-06","cited_by_count":11,"area":"offlinerl"},{"id":"2601.16973","title":"VisGym: Diverse, Customizable, Scalable Environments for Multimodal Agents","created":"2026-01-23","cited_by_count":11,"area":"mllm"},{"id":"2306.16688","title":"SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores","created":"2023-06-29","cited_by_count":10,"area":null},{"id":"2403.01499","title":"Normalizing Flow-based Differentiable Particle Filters","created":"2024-03-03","cited_by_count":10,"area":null},{"id":"2411.07690","title":"World Models: The Safety Perspective","created":"2024-11-12","cited_by_count":9,"area":"wm"},{"id":"2108.02846","title":"Communicative Learning with Natural Gestures for Embodied Navigation Agents with Human-in-the-Scene","created":"2021-08-05","cited_by_count":7,"area":null},{"id":"2302.07350","title":"Graph schemas as abstractions for transfer learning, inference, and planning","created":"2023-02-14","cited_by_count":7,"area":null},{"id":"2206.05751","title":"Consistent Attack: Universal Adversarial Perturbation on Embodied Vision Navigation","created":"2022-06-12","cited_by_count":6,"area":null},{"id":"2312.02923","title":"MoSA: Mixture of Sparse Adapters for Visual Efficient Tuning","created":"2023-12-05","cited_by_count":6,"area":null},{"id":"2408.06798","title":"Token Compensator: Altering Inference Cost of Vision Transformer without Re-Tuning","created":"2024-08-13","cited_by_count":6,"area":"inference"},{"id":"2607.24744","title":"Data Pyramid for Embodied Manipulation: A Survey","created":"2026-07-27","cited_by_count":6,"area":null},{"id":"2112.11731","title":"Graph augmented Deep Reinforcement Learning in the GameRLand3D environment","created":"2021-12-22","cited_by_count":5,"area":null},{"id":"2203.16777","title":"Mask Atari for Deep Reinforcement Learning as POMDP Benchmarks","created":"2022-03-31","cited_by_count":5,"area":null},{"id":"2112.03636","title":"Godot Reinforcement Learning Agents","created":"2021-12-07","cited_by_count":4,"area":null},{"id":"2207.02518","title":"Compositional Generalization in Grounded Language Learning via Induced Model Sparsity","created":"2022-07-06","cited_by_count":4,"area":null},{"id":"2209.10055","title":"Lamarckian Platform: Pushing the Boundaries of Evolutionary Reinforcement Learning towards Asynchronous Commercial Games","created":"2022-09-21","cited_by_count":4,"area":null},{"id":"2404.15721","title":"SPARO: Selective Attention for Robust and Compositional Transformer Encodings for Vision","created":"2024-04-24","cited_by_count":4,"area":null},{"id":"2410.14616","title":"Benchmarking Deep Reinforcement Learning for Navigation in Denied Sensor Environments","created":"2024-10-18","cited_by_count":4,"area":"deeprl"},{"id":"2412.08341","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","created":"2024-12-11","cited_by_count":4,"area":null},{"id":"2607.06701","title":"SPEAR: A Simulator for Photorealistic Embodied AI Research","created":"2026-07-07","cited_by_count":4,"area":null},{"id":"2102.04916","title":"rl_reach: Reproducible Reinforcement Learning Experiments for Robotic Reaching Tasks","created":"2021-02-09","cited_by_count":3,"area":null},{"id":"2603.06413","title":"A Reference Architecture of Reinforcement Learning Frameworks","created":"2026-03-06","cited_by_count":3,"area":"deeprl"},{"id":"2109.08465","title":"Messing Up 3D Virtual Environments: Transferable Adversarial 3D Objects","created":"2021-09-17","cited_by_count":2,"area":null},{"id":"2403.15750","title":"iDAT: inverse Distillation Adapter-Tuning","created":"2024-03-23","cited_by_count":2,"area":"distill"},{"id":"2405.01251","title":"Revisiting semi-supervised training objectives for differentiable particle filters","created":"2024-05-02","cited_by_count":2,"area":null},{"id":"2412.12024","title":"Learning to Navigate in Mazes with Novel Layouts using Abstract Top-down Maps","created":"2024-12-16","cited_by_count":2,"area":null},{"id":"2506.21782","title":"M3PO: Massively Multi-Task Model-Based Policy Optimization","created":"2025-06-26","cited_by_count":2,"area":"deeprl"},{"id":"2507.15716","title":"DiffPF: Differentiable Particle Filtering with Generative Sampling via Conditional Diffusion Models","created":"2025-07-21","cited_by_count":2,"area":"diffusion"},{"id":"2510.25693","title":"PyDPF: A Python Package for Differentiable Particle Filtering","created":"2025-10-29","cited_by_count":2,"area":null},{"id":"2201.04279","title":"Dynamical Audio-Visual Navigation: Catching Unheard Moving Sound Sources in Unmapped 3D Environments","created":"2022-01-12","cited_by_count":1,"area":null},{"id":"2209.02066","title":"Trust in Language Grounding: a new AI challenge for human-robot teams","created":"2022-09-05","cited_by_count":1,"area":null},{"id":"2304.13639","title":"PVP: Pre-trained Visual Parameter-Efficient Tuning","created":"2023-04-26","cited_by_count":1,"area":null},{"id":"2411.13072","title":"AMaze: An intuitive benchmark generator for fast prototyping of generalizable agents","created":"2024-11-20","cited_by_count":1,"area":null},{"id":"2502.06779","title":"KARST: Multi-Kernel Kronecker Adaptation with Re-Scaling Transmission for Visual Classification","created":"2025-02-10","cited_by_count":1,"area":null},{"id":"2507.09495","title":"GenAI-based Multi-Agent Reinforcement Learning towards Distributed Agent Intelligence: A Generative-RL Agent Perspective","created":"2025-07-13","cited_by_count":1,"area":null},{"id":"2510.16446","title":"VIPAMIN: Visual Prompt Initialization via Embedding Selection and Subspace Expansion","created":"2025-10-18","cited_by_count":1,"area":null},{"id":"2512.08139","title":"Robust Agents in Open-Ended Worlds","created":"2025-12-09","cited_by_count":1,"area":"agents"},{"id":"2601.15086","title":"Memory Retention Is Not Enough to Master Memory Tasks in Reinforcement Learning","created":"2026-01-21","cited_by_count":1,"area":"deeprl"},{"id":"2203.13424","title":"Dealing with Sparse Rewards Using Graph Neural Networks","created":"2022-03-25","cited_by_count":0,"area":null},{"id":"2210.01235","title":"CaiRL: A High-Performance Reinforcement Learning Environment Toolkit","created":"2022-10-03","cited_by_count":0,"area":null},{"id":"2302.13483","title":"CrystalBox: Future-Based Explanations for Input-Driven Deep RL Systems","created":"2023-02-27","cited_by_count":0,"area":null},{"id":"2303.07397","title":"Fast exploration and learning of latent graphs with aliased observations","created":"2023-03-13","cited_by_count":0,"area":null},{"id":"2304.02738","title":"Core Challenges in Embodied Vision-Language Planning","created":"2023-04-05","cited_by_count":0,"area":null},{"id":"2402.06023","title":"Decision Theory-Guided Deep Reinforcement Learning for Fast Learning","created":"2024-02-08","cited_by_count":0,"area":"deeprl"},{"id":"2506.11042","title":"GenFT: A Generative Parameter-Efficient Fine-Tuning Method for Pretrained Foundation Models","created":"2025-05-21","cited_by_count":0,"area":null},{"id":"2512.07703","title":"PVeRA: Probabilistic Vector-Based Random Matrix Adaptation","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2512.16444","title":"StarCraft+: Benchmarking Multi-agent Algorithms in Adversary Paradigm","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2603.23964","title":"From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environments","created":"2026-03-25","cited_by_count":0,"area":"lr"},{"id":"2609.16737","title":"Visual Cue Guided Video Planning for Generalizable Robot Navigation","created":"2026-09-15","cited_by_count":0,"area":null}],"next_cursor":null}