{"list":"other","total":71,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"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":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"1811.12231","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","created":"2018-11-29","cited_by_count":1432},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"2404.02905","title":"Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction","created":"2024-04-03","cited_by_count":1023},{"id":"1807.04975","title":"Recognition in Terra Incognita","created":"2018-07-13","cited_by_count":658},{"id":"2302.00111","title":"Learning Universal Policies via Text-Guided Video Generation","created":"2023-01-31","cited_by_count":522},{"id":"2402.10329","title":"Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots","created":"2024-02-15","cited_by_count":394},{"id":"1904.12584","title":"The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision","created":"2019-04-26","cited_by_count":372},{"id":"2509.20328","title":"Video models are zero-shot learners and reasoners","created":"2025-09-24","cited_by_count":220},{"id":"2412.12392","title":"MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors","created":"2024-12-16","cited_by_count":205},{"id":"2404.12377","title":"RoboDreamer: Learning Compositional World Models for Robot Imagination","created":"2024-04-18","cited_by_count":195},{"id":"2504.00983","title":"WorldScore: A Unified Evaluation Benchmark for World Generation","created":"2025-04-01","cited_by_count":156},{"id":"2211.12497","title":"MagicPony: Learning Articulated 3D Animals in the Wild","created":"2022-11-22","cited_by_count":112},{"id":"2504.20995","title":"TesserAct: Learning 4D Embodied World Models","created":"2025-04-29","cited_by_count":94},{"id":"2603.22435","title":"CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation","created":"2026-03-23","cited_by_count":88},{"id":"2402.17139","title":"Video as the New Language for Real-World Decision Making","created":"2024-02-27","cited_by_count":87},{"id":"2411.17735","title":"3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning","created":"2024-11-23","cited_by_count":75},{"id":"2512.15840","title":"Large Video Planner Enables Generalizable Robot Control","created":"2025-12-17","cited_by_count":70},{"id":"1801.04016","title":"Theoretical Impediments to Machine Learning With Seven Sparks from the Causal Revolution","created":"2018-01-11","cited_by_count":66},{"id":"2401.02400","title":"Learning the 3D Fauna of the Web","created":"2024-01-04","cited_by_count":59},{"id":"2403.08632","title":"A Decade's Battle on Dataset Bias: Are We There Yet?","created":"2024-03-13","cited_by_count":47},{"id":"2105.01060","title":"Curious Representation Learning for Embodied Intelligence","created":"2021-05-03","cited_by_count":44},{"id":"2510.26802","title":"Are Video Models Ready as Zero-Shot Reasoners? An Empirical Study with the MME-CoF Benchmark","created":"2025-10-30","cited_by_count":43},{"id":"2511.04570","title":"Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm","created":"2025-11-06","cited_by_count":42},{"id":"2402.01103","title":"Compositional Generative Modeling: A Single Model is Not All You Need","created":"2024-02-02","cited_by_count":41},{"id":"2603.03276","title":"Beyond Language Modeling: An Exploration of Multimodal Pretraining","created":"2026-03-03","cited_by_count":37},{"id":"1803.11288","title":"FutureMapping: The Computational Structure of Spatial AI Systems","created":"2018-03-29","cited_by_count":36},{"id":"2410.16770","title":"The Scene Language: Representing Scenes with Programs, Words, and Embeddings","created":"2024-10-22","cited_by_count":36},{"id":"2602.20159","title":"A Very Big Video Reasoning Suite","created":"2026-02-23","cited_by_count":34},{"id":"2310.16035","title":"What's Left? Concept Grounding with Logic-Enhanced Foundation Models","created":"2023-10-24","cited_by_count":33},{"id":"2605.15187","title":"Articraft: An Agentic System for Scalable Articulated 3D Asset Generation","created":"2026-05-14","cited_by_count":30},{"id":"2505.06227","title":"Anymate: A Dataset and Baselines for Learning 3D Object Rigging","created":"2025-05-09","cited_by_count":27},{"id":"2512.11798","title":"Particulate: Feed-Forward 3D Object Articulation","created":"2025-12-12","cited_by_count":23},{"id":"2511.13853","title":"Can World Simulators Reason? Gen-ViRe: A Generative Visual Reasoning Benchmark","created":"2025-11-17","cited_by_count":19},{"id":"2604.01985","title":"World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry","created":"2026-04-02","cited_by_count":18},{"id":"1910.14139","title":"FutureMapping 2: Gaussian Belief Propagation for Spatial AI","created":"2019-10-30","cited_by_count":17},{"id":"2412.01876","title":"Understanding Bias in Large-Scale Visual Datasets","created":"2024-12-02","cited_by_count":15},{"id":"2511.20937","title":"ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction","created":"2025-11-26","cited_by_count":15},{"id":"2212.04965","title":"Seeing a Rose in Five Thousand Ways","created":"2022-12-09","cited_by_count":13},{"id":"2303.07308","title":"NeuSE: Neural SE(3)-Equivariant Embedding for Long-Term Object-Based Simultaneous Localization and Mapping","created":"2023-03-13","cited_by_count":10},{"id":"2505.06191","title":"Building Intelligent Agents with Neuro-Symbolic Concepts","created":"2025-05-09","cited_by_count":10},{"id":"2603.30043","title":"Video Models Reason Early: Exploiting Plan Commitment for Maze Solving","created":"2026-03-31","cited_by_count":9},{"id":"2605.15458","title":"Video Models Can Reason with Verifiable Rewards","created":"2026-05-14","cited_by_count":9},{"id":"2412.05278","title":"Birth and Death of a Rose","created":"2024-12-06","cited_by_count":7},{"id":"2506.06658","title":"Self-Improving Loops for Visual Robotic Planning","created":"2025-06-07","cited_by_count":7},{"id":"2103.17273","title":"Fast and Accurate Emulation of the SDO/HMI Stokes Inversion with Uncertainty Quantification","created":"2021-03-31","cited_by_count":5},{"id":"2601.04194","title":"Choreographing a World of Dynamic Objects","created":"2026-01-07","cited_by_count":5},{"id":"2011.03183","title":"Learning Object-Based State Estimators for Household Robots","created":"2020-11-06","cited_by_count":4},{"id":"2511.19435","title":"Are Image-to-Video Models Good Zero-Shot Image Editors?","created":"2025-11-24","cited_by_count":4},{"id":"2604.02327","title":"Steerable Visual Representations","created":"2026-04-02","cited_by_count":4},{"id":"2605.08735","title":"CollabVR: Collaborative Video Reasoning with Vision-Language and Video Generation Models","created":"2026-05-09","cited_by_count":4},{"id":"2606.13676","title":"Modality Forcing for Scalable Spatial Generation","created":"2026-06-11","cited_by_count":4},{"id":"2606.14699","title":"Instruct-Particulate: Scaling Feed-Forward 3D Object Articulation with Kinematic Control","created":"2026-06-12","cited_by_count":4},{"id":"2505.21780","title":"Compositional Scene Understanding through Inverse Generative Modeling","created":"2025-05-27","cited_by_count":3},{"id":"2605.30347","title":"NeuROK: Generative 4D Neural Object Kinematics","created":"2026-05-28","cited_by_count":3},{"id":"2607.01166","title":"Structured 4D Latent Predictive Model for Robot Planning","created":"2026-07-01","cited_by_count":3}],"next_cursor":null}