{"list":"other","total":51,"rows":[{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"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":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"2307.06281","title":"MMBench: Is Your Multi-modal Model an All-around Player?","created":"2023-07-12","cited_by_count":2141},{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856},{"id":"2209.07753","title":"Code as Policies: Language Model Programs for Embodied Control","created":"2022-09-16","cited_by_count":1210},{"id":"2306.13063","title":"Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs","created":"2023-06-22","cited_by_count":974},{"id":"2302.09664","title":"Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation","created":"2023-02-19","cited_by_count":819},{"id":"2305.14975","title":"Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback","created":"2023-05-24","cited_by_count":812},{"id":"2205.14334","title":"Teaching Models to Express Their Uncertainty in Words","created":"2022-05-28","cited_by_count":751},{"id":"2307.05973","title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","created":"2023-07-12","cited_by_count":750},{"id":"2401.12168","title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities","created":"2024-01-22","cited_by_count":706},{"id":"2109.08238","title":"Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI","created":"2021-09-16","cited_by_count":592},{"id":"2407.07895","title":"LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models","created":"2024-07-10","cited_by_count":584},{"id":"2210.05714","title":"Visual Language Maps for Robot Navigation","created":"2022-10-11","cited_by_count":365},{"id":"2311.12871","title":"An Embodied Generalist Agent in 3D World","created":"2023-11-18","cited_by_count":365},{"id":"2402.07865","title":"Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models","created":"2024-02-12","cited_by_count":339},{"id":"1711.11543","title":"Embodied Question Answering","created":"2017-11-30","cited_by_count":336},{"id":"2210.07474","title":"SQA3D: Situated Question Answering in 3D Scenes","created":"2022-10-14","cited_by_count":314},{"id":"2307.01928","title":"Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners","created":"2023-07-04","cited_by_count":308},{"id":"2205.06230","title":"Simple Open-Vocabulary Object Detection with Vision Transformers","created":"2022-05-12","cited_by_count":305},{"id":"2305.16986","title":"NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models","created":"2023-05-26","cited_by_count":280},{"id":"2402.15852","title":"NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation","created":"2024-02-24","cited_by_count":233},{"id":"2310.13724","title":"Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots","created":"2023-10-19","cited_by_count":228},{"id":"2408.16500","title":"CogVLM2: Visual Language Models for Image and Video Understanding","created":"2024-08-29","cited_by_count":217},{"id":"2012.14983","title":"Reducing conversational agents' overconfidence through linguistic calibration","created":"2020-12-30","cited_by_count":210},{"id":"2312.03275","title":"VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigation","created":"2023-12-06","cited_by_count":205},{"id":"2203.10421","title":"CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation","created":"2022-03-20","cited_by_count":194},{"id":"2309.02561","title":"Physically Grounded Vision-Language Models for Robotic Manipulation","created":"2023-09-05","cited_by_count":165},{"id":"2312.16217","title":"ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulation","created":"2023-12-24","cited_by_count":162},{"id":"2209.09874","title":"Open-vocabulary Queryable Scene Representations for Real World Planning","created":"2022-09-20","cited_by_count":160},{"id":"1712.03316","title":"IQA: Visual Question Answering in Interactive Environments","created":"2017-12-09","cited_by_count":155},{"id":"1505.02074","title":"Exploring Models and Data for Image Question Answering","created":"2015-05-08","cited_by_count":139},{"id":"1607.05910","title":"Visual Question Answering: A Survey of Methods and Datasets","created":"2016-07-20","cited_by_count":123},{"id":"1904.03461","title":"Embodied Question Answering in Photorealistic Environments with Point Cloud Perception","created":"2019-04-06","cited_by_count":103},{"id":"2310.10103","title":"Navigation with Large Language Models: Semantic Guesswork as a Heuristic for Planning","created":"2023-10-16","cited_by_count":89},{"id":"1904.04686","title":"Multi-Target Embodied Question Answering","created":"2019-04-09","cited_by_count":74},{"id":"2403.15941","title":"Explore until Confident: Efficient Exploration for Embodied Question Answering","created":"2024-03-23","cited_by_count":74},{"id":"2409.14296","title":"HM3D-OVON: A Dataset and Benchmark for Open-Vocabulary Object Goal Navigation","created":"2024-09-22","cited_by_count":71},{"id":"2403.01216","title":"API Is Enough: Conformal Prediction for Large Language Models Without Logit-Access","created":"2024-03-02","cited_by_count":69},{"id":"2303.11327","title":"3D Concept Learning and Reasoning from Multi-View Images","created":"2023-03-20","cited_by_count":60},{"id":"1610.01465","title":"Visual Question Answering: Datasets, Algorithms, and Future Challenges","created":"2016-10-05","cited_by_count":56},{"id":"1810.11181","title":"Neural Modular Control for Embodied Question Answering","created":"2018-10-26","cited_by_count":56},{"id":"1908.04950","title":"VideoNavQA: Bridging the Gap between Visual and Embodied Question Answering","created":"2019-08-14","cited_by_count":12},{"id":"2408.01867","title":"TrustNavGPT: Modeling Uncertainty to Improve Trustworthiness of Audio-Guided LLM-Based Robot Navigation","created":"2024-08-03","cited_by_count":11},{"id":"2312.06408","title":"DiffVL: Scaling Up Soft Body Manipulation using Vision-Language Driven Differentiable Physics","created":"2023-12-11","cited_by_count":6}],"next_cursor":null}