{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2303.04137","title":"Diffusion Policy: Visuomotor Policy Learning via Action Diffusion","created":"2023-03-07","cited_by_count":2838},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2304.13705","title":"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware","created":"2023-04-23","cited_by_count":1568},{"id":"2405.12213","title":"Octo: An Open-Source Generalist Robot Policy","created":"2024-05-20","cited_by_count":1484},{"id":"2306.03310","title":"LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning","created":"2023-06-05","cited_by_count":1410},{"id":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"id":"2205.09991","title":"Planning with Diffusion for Flexible Behavior Synthesis","created":"2022-05-20","cited_by_count":1061},{"id":"2309.16588","title":"Vision Transformers Need Registers","created":"2023-09-28","cited_by_count":871},{"id":"2108.03298","title":"What Matters in Learning from Offline Human Demonstrations for Robot Manipulation","created":"2021-08-06","cited_by_count":725},{"id":"2501.09747","title":"FAST: Efficient Action Tokenization for Vision-Language-Action Models","created":"2025-01-16","cited_by_count":665},{"id":"2406.11838","title":"Autoregressive Image Generation without Vector Quantization","created":"2024-06-17","cited_by_count":651},{"id":"2105.13626","title":"ByT5: Towards a token-free future with pre-trained byte-to-byte models","created":"2021-05-28","cited_by_count":509},{"id":"2309.15505","title":"Finite Scalar Quantization: VQ-VAE Made Simple","created":"2023-09-27","cited_by_count":440},{"id":"2406.02523","title":"RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots","created":"2024-06-04","cited_by_count":407},{"id":"2409.12514","title":"TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation","created":"2024-09-19","cited_by_count":339},{"id":"2406.07550","title":"An Image is Worth 32 Tokens for Reconstruction and Generation","created":"2024-06-11","cited_by_count":302},{"id":"2205.13147","title":"Matryoshka Representation Learning","created":"2022-05-26","cited_by_count":282},{"id":"2304.02532","title":"Goal-Conditioned Imitation Learning using Score-based Diffusion Policies","created":"2023-04-05","cited_by_count":236},{"id":"2502.06768","title":"Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions","created":"2025-02-10","cited_by_count":214},{"id":"1901.07821","title":"Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoff","created":"2019-01-23","cited_by_count":211},{"id":"2503.10631","title":"HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model","created":"2025-03-13","cited_by_count":181},{"id":"2403.03181","title":"Behavior Generation with Latent Actions","created":"2024-03-05","cited_by_count":160},{"id":"2403.09227","title":"BEHAVIOR-1K: A Human-Centered, Embodied AI Benchmark with 1,000 Everyday Activities and Realistic Simulation","created":"2024-03-14","cited_by_count":148},{"id":"1812.05069","title":"Recent Advances in Autoencoder-Based Representation Learning","created":"2018-12-12","cited_by_count":133},{"id":"2502.13967","title":"FlexTok: Resampling Images into 1D Token Sequences of Flexible Length","created":"2025-02-19","cited_by_count":110},{"id":"2011.02268","title":"Causal Autoregressive Flows","created":"2020-11-04","cited_by_count":99},{"id":"1402.0915","title":"Learning Ordered Representations with Nested Dropout","created":"2014-02-05","cited_by_count":84},{"id":"2405.17430","title":"Matryoshka Multimodal Models","created":"2024-05-27","cited_by_count":84},{"id":"2205.10337","title":"UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes","created":"2022-05-20","cited_by_count":78},{"id":"2407.15840","title":"QueST: Self-Supervised Skill Abstractions for Learning Continuous Control","created":"2024-07-22","cited_by_count":53},{"id":"2504.21530","title":"RoboGround: Robotic Manipulation with Grounded Vision-Language Priors","created":"2025-04-30","cited_by_count":51},{"id":"2504.08438","title":"Diffusion Models for Robotic Manipulation: A Survey","created":"2025-04-11","cited_by_count":41},{"id":"2506.15666","title":"Vision in Action: Learning Active Perception from Human Demonstrations","created":"2025-06-18","cited_by_count":37},{"id":"2411.03990","title":"ET-SEED: Efficient Trajectory-Level SE(3) Equivariant Diffusion Policy","created":"2024-11-06","cited_by_count":26},{"id":"2410.21154","title":"Trajectory Flow Matching with Applications to Clinical Time Series Modeling","created":"2024-10-28","cited_by_count":24},{"id":"2502.04296","title":"Learning Real-World Action-Video Dynamics with Heterogeneous Masked Autoregression","created":"2025-02-06","cited_by_count":23},{"id":"2507.09061","title":"Action Chunking and Exploratory Data Collection Yield Exponential Improvements in Behavior Cloning for Continuous Control","created":"2025-07-11","cited_by_count":15},{"id":"2512.06951","title":"Task adaptation of Vision-Language-Action model: 1st Place Solution for the 2025 BEHAVIOR Challenge","created":"2025-12-07","cited_by_count":15},{"id":"2509.23468","title":"Multi-Modal Manipulation via Multi-Modal Policy Consensus","created":"2025-09-27","cited_by_count":13},{"id":"2509.02530","title":"Manipulation as in Simulation: Enabling Accurate Geometry Perception in Robots","created":"2025-09-02","cited_by_count":11},{"id":"2305.18464","title":"Bridging the Sim-to-Real Gap from the Information Bottleneck Perspective","created":"2023-05-29","cited_by_count":10},{"id":"2503.23271","title":"Learning Coordinated Bimanual Manipulation Policies using State Diffusion and Inverse Dynamics Models","created":"2025-03-30","cited_by_count":9},{"id":"2504.04612","title":"Tool-as-Interface: Learning Robot Policies from Observing Human Tool Use","created":"2025-04-06","cited_by_count":8},{"id":"2509.21983","title":"Hybrid Diffusion for Simultaneous Symbolic and Continuous Planning","created":"2025-09-26","cited_by_count":7},{"id":"2409.18581","title":"Deep Autoregressive Models as Causal Inference Engines","created":"2024-09-27","cited_by_count":6},{"id":"2512.14697","title":"Spherical Leech Quantization for Visual Tokenization and Generation","created":"2025-12-16","cited_by_count":6},{"id":"2512.21898","title":"Flexible Multitask Learning with Factorized Diffusion Policy","created":"2025-12-26","cited_by_count":5}],"next_cursor":null}