{"list":"other","total":73,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"1409.1259","title":"On the Properties of Neural Machine Translation: Encoder-Decoder Approaches","created":"2014-09-03","cited_by_count":1304},{"id":"2209.07753","title":"Code as Policies: Language Model Programs for Embodied Control","created":"2022-09-16","cited_by_count":1210},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"2207.05608","title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","created":"2022-07-12","cited_by_count":1081},{"id":"2201.07207","title":"Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents","created":"2022-01-18","cited_by_count":1035},{"id":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"2106.13884","title":"Multimodal Few-Shot Learning with Frozen Language Models","created":"2021-06-25","cited_by_count":661},{"id":"2106.02039","title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","created":"2021-06-03","cited_by_count":644},{"id":"2209.11302","title":"ProgPrompt: Generating Situated Robot Task Plans using Large Language Models","created":"2022-09-22","cited_by_count":611},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"id":"2111.09734","title":"ClipCap: CLIP Prefix for Image Captioning","created":"2021-11-18","cited_by_count":559},{"id":"2302.14045","title":"Language Is Not All You Need: Aligning Perception with Language Models","created":"2023-02-27","cited_by_count":543},{"id":"1712.04851","title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","created":"2017-12-13","cited_by_count":521},{"id":"2106.14405","title":"Habitat 2.0: Training Home Assistants to Rearrange their Habitat","created":"2021-06-28","cited_by_count":511},{"id":"2206.08916","title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","created":"2022-06-17","cited_by_count":421},{"id":"2210.03094","title":"VIMA: General Robot Manipulation with Multimodal Prompts","created":"2022-10-06","cited_by_count":407},{"id":"1912.10077","title":"Are Transformers universal approximators of sequence-to-sequence functions?","created":"2019-12-20","cited_by_count":406},{"id":"1707.08817","title":"Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards","created":"2017-07-27","cited_by_count":319},{"id":"1903.02874","title":"COIN: A Large-scale Dataset for Comprehensive Instructional Video Analysis","created":"2019-03-07","cited_by_count":318},{"id":"2006.06669","title":"Understanding Human Hands in Contact at Internet Scale","created":"2020-06-11","cited_by_count":281},{"id":"2103.04918","title":"A Survey of Embodied AI: From Simulators to Research Tasks","created":"2021-03-08","cited_by_count":261},{"id":"2202.01771","title":"Pre-Trained Language Models for Interactive Decision-Making","created":"2022-02-03","cited_by_count":221},{"id":"1605.08104","title":"Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning","created":"2016-05-25","cited_by_count":204},{"id":"2106.02036","title":"Anticipative Video Transformer","created":"2021-06-03","cited_by_count":200},{"id":"1903.08225","title":"Cross-task weakly supervised learning from instructional videos","created":"2019-03-19","cited_by_count":199},{"id":"1706.08033","title":"Decomposing Motion and Content for Natural Video Sequence Prediction","created":"2017-06-25","cited_by_count":169},{"id":"2108.03332","title":"BEHAVIOR: Benchmark for Everyday Household Activities in Virtual, Interactive, and Ecological Environments","created":"2021-08-06","cited_by_count":165},{"id":"2105.06453","title":"Episodic Transformer for Vision-and-Language Navigation","created":"2021-05-13","cited_by_count":156},{"id":"2201.07520","title":"CM3: A Causal Masked Multimodal Model of the Internet","created":"2022-01-19","cited_by_count":142},{"id":"2001.04583","title":"EGO-TOPO: Environment Affordances from Egocentric Video","created":"2020-01-14","cited_by_count":111},{"id":"2204.01696","title":"Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos","created":"2022-04-04","cited_by_count":111},{"id":"1804.00892","title":"When will you do what? - Anticipating Temporal Occurrences of Activities","created":"2018-04-03","cited_by_count":107},{"id":"1905.09035","title":"What Would You Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality Attention","created":"2019-05-22","cited_by_count":105},{"id":"2012.03912","title":"MultiON: Benchmarking Semantic Map Memory using Multi-Object Navigation","created":"2020-12-07","cited_by_count":95},{"id":"1907.01172","title":"Procedure Planning in Instructional Videos","created":"2019-07-02","cited_by_count":92},{"id":"2302.00763","title":"Collaborating with language models for embodied reasoning","created":"2023-02-01","cited_by_count":61},{"id":"2107.11444","title":"Cooperative Exploration for Multi-Agent Deep Reinforcement Learning","created":"2021-07-23","cited_by_count":57},{"id":"1904.05250","title":"Next-Active-Object prediction from Egocentric Videos","created":"2019-04-10","cited_by_count":55},{"id":"2008.12760","title":"AllenAct: A Framework for Embodied AI Research","created":"2020-08-28","cited_by_count":54},{"id":"2110.01770","title":"Procedure Planning in Instructional Videos via Contextual Modeling and Model-based Policy Learning","created":"2021-10-05","cited_by_count":53},{"id":"2007.04979","title":"A Cordial Sync: Going Beyond Marginal Policies for Multi-Agent Embodied Tasks","created":"2020-07-09","cited_by_count":52},{"id":"2112.09120","title":"Human Hands as Probes for Interactive Object Understanding","created":"2021-12-16","cited_by_count":52},{"id":"2205.02300","title":"P3IV: Probabilistic Procedure Planning from Instructional Videos with Weak Supervision","created":"2022-05-04","cited_by_count":52},{"id":"2211.09529","title":"InternVideo-Ego4D: A Pack of Champion Solutions to Ego4D Challenges","created":"2022-11-17","cited_by_count":48},{"id":"2210.06849","title":"Retrospectives on the Embodied AI Workshop","created":"2022-10-13","cited_by_count":46},{"id":"1904.05879","title":"Two Body Problem: Collaborative Visual Task Completion","created":"2019-04-11","cited_by_count":45},{"id":"2109.04869","title":"PlaTe: Visually-Grounded Planning with Transformers in Procedural Tasks","created":"2021-09-10","cited_by_count":45},{"id":"1812.02501","title":"Zero-Shot Anticipation for Instructional Activities","created":"2018-12-06","cited_by_count":43},{"id":"2009.01142","title":"Long-Term Anticipation of Activities with Cycle Consistency","created":"2020-09-02","cited_by_count":40},{"id":"2205.12258","title":"History Compression via Language Models in Reinforcement Learning","created":"2022-05-24","cited_by_count":39},{"id":"2007.12173","title":"Bridging the Imitation Gap by Adaptive Insubordination","created":"2020-07-23","cited_by_count":38},{"id":"2207.12080","title":"Intention-Conditioned Long-Term Human Egocentric Action Forecasting","created":"2022-07-25","cited_by_count":35},{"id":"2110.03303","title":"Universal Approximation Under Constraints is Possible with Transformers","created":"2021-10-07","cited_by_count":32},{"id":"1904.03273","title":"A Variational Auto-Encoder Model for Stochastic Point Processes","created":"2019-04-05","cited_by_count":30},{"id":"2209.13583","title":"Learning State-Aware Visual Representations from Audible Interactions","created":"2022-09-27","cited_by_count":23},{"id":"2104.08251","title":"proScript: Partially Ordered Scripts Generation via Pre-trained Language Models","created":"2021-04-16","cited_by_count":21},{"id":"2105.00931","title":"GridToPix: Training Embodied Agents with Minimal Supervision","created":"2021-04-14","cited_by_count":21},{"id":"1603.04908","title":"First Person Action-Object Detection with EgoNet","created":"2016-03-15","cited_by_count":17},{"id":"2301.04647","title":"EXIF as Language: Learning Cross-Modal Associations Between Images and Camera Metadata","created":"2023-01-11","cited_by_count":17},{"id":"2106.03158","title":"Transferring Knowledge from Text to Video: Zero-Shot Anticipation for Procedural Actions","created":"2021-06-06","cited_by_count":10},{"id":"2302.05330","title":"Action Dynamics Task Graphs for Learning Plannable Representations of Procedural Tasks","created":"2023-01-11","cited_by_count":8}],"next_cursor":null}