{"list":"other","total":66,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"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":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"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":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"1904.05866","title":"Expressive Body Capture: 3D Hands, Face, and Body from a Single Image","created":"2019-04-11","cited_by_count":1612},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"1912.06670","title":"Common Voice: A Massively-Multilingual Speech Corpus","created":"2019-12-13","cited_by_count":1384},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"id":"2107.03312","title":"SoundStream: An End-to-End Neural Audio Codec","created":"2021-07-07","cited_by_count":771},{"id":"2312.07533","title":"VILA: On Pre-training for Visual Language Models","created":"2023-12-12","cited_by_count":692},{"id":"2209.03143","title":"AudioLM: a Language Modeling Approach to Audio Generation","created":"2022-09-07","cited_by_count":616},{"id":"2305.11000","title":"SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities","created":"2023-05-18","cited_by_count":529},{"id":"2306.14795","title":"MotionGPT: Human Motion as a Foreign Language","created":"2023-06-26","cited_by_count":527},{"id":"2312.14125","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","created":"2023-12-21","cited_by_count":492},{"id":"2101.08779","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","created":"2021-01-21","cited_by_count":485},{"id":"2110.04596","title":"Deep Long-Tailed Learning: A Survey","created":"2021-10-09","cited_by_count":417},{"id":"2311.12871","title":"An Embodied Generalist Agent in 3D World","created":"2023-11-18","cited_by_count":365},{"id":"2312.13139","title":"Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation","created":"2023-12-20","cited_by_count":364},{"id":"2201.10005","title":"Text and Code Embeddings by Contrastive Pre-Training","created":"2022-01-24","cited_by_count":361},{"id":"2310.10158","title":"Character-LLM: A Trainable Agent for Role-Playing","created":"2023-10-16","cited_by_count":339},{"id":"2306.08647","title":"Language to Rewards for Robotic Skill Synthesis","created":"2023-06-14","cited_by_count":312},{"id":"2410.06158","title":"GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation","created":"2024-10-08","cited_by_count":296},{"id":"2402.12226","title":"AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling","created":"2024-02-19","cited_by_count":217},{"id":"2304.05684","title":"InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions","created":"2023-04-12","cited_by_count":206},{"id":"2211.09707","title":"Listen, Denoise, Action! Audio-Driven Motion Synthesis with Diffusion Models","created":"2022-11-17","cited_by_count":190},{"id":"2406.04904","title":"XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model","created":"2024-06-07","cited_by_count":179},{"id":"2203.05297","title":"BEAT: A Large-Scale Semantic and Emotional Multi-Modal Dataset for Conversational Gestures Synthesis","created":"2022-03-10","cited_by_count":178},{"id":"2309.17448","title":"SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation","created":"2023-09-29","cited_by_count":155},{"id":"2401.04092","title":"GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generation","created":"2024-01-08","cited_by_count":153},{"id":"2409.16283","title":"Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation","created":"2024-09-24","cited_by_count":153},{"id":"2306.10900","title":"MotionGPT: Finetuned LLMs Are General-Purpose Motion Generators","created":"2023-06-19","cited_by_count":145},{"id":"2407.01512","title":"Open-TeleVision: Teleoperation with Immersive Active Visual Feedback","created":"2024-07-01","cited_by_count":145},{"id":"2401.01275","title":"CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluation","created":"2024-01-02","cited_by_count":143},{"id":"2402.17766","title":"ShapeLLM: Universal 3D Object Understanding for Embodied Interaction","created":"2024-02-27","cited_by_count":137},{"id":"2310.00704","title":"UniAudio: An Audio Foundation Model Toward Universal Audio Generation","created":"2023-10-01","cited_by_count":127},{"id":"2305.09636","title":"SoundStorm: Efficient Parallel Audio Generation","created":"2023-05-16","cited_by_count":114},{"id":"2310.12978","title":"HumanTOMATO: Text-aligned Whole-body Motion Generation","created":"2023-10-19","cited_by_count":104},{"id":"2312.16051","title":"Inter-X: Towards Versatile Human-Human Interaction Analysis","created":"2023-12-26","cited_by_count":98},{"id":"2308.16692","title":"SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models","created":"2023-08-31","cited_by_count":87},{"id":"2401.01885","title":"From Audio to Photoreal Embodiment: Synthesizing Humans in Conversations","created":"2024-01-03","cited_by_count":82},{"id":"2209.09391","title":"QuestSim: Human Motion Tracking from Sparse Sensors with Simulated Avatars","created":"2022-09-20","cited_by_count":77},{"id":"2311.18836","title":"ChatPose: Chatting about 3D Human Pose","created":"2023-11-30","cited_by_count":72},{"id":"2311.16468","title":"AvatarGPT: All-in-One Framework for Motion Understanding, Planning, Generation and Beyond","created":"2023-11-28","cited_by_count":63},{"id":"2303.17368","title":"SynBody: Synthetic Dataset with Layered Human Models for 3D Human Perception and Modeling","created":"2023-03-30","cited_by_count":54},{"id":"2403.18811","title":"Duolando: Follower GPT with Off-Policy Reinforcement Learning for Dance Accompaniment","created":"2024-03-27","cited_by_count":47},{"id":"2312.04547","title":"Digital Life Project: Autonomous 3D Characters with Social Intelligence","created":"2023-12-07","cited_by_count":43},{"id":"2410.08328","title":"Agents Thinking Fast and Slow: A Talker-Reasoner Architecture","created":"2024-10-10","cited_by_count":36},{"id":"2312.01479","title":"OpenVoice: Versatile Instant Voice Cloning","created":"2023-12-03","cited_by_count":32},{"id":"2408.00762","title":"UniTalker: Scaling up Audio-Driven 3D Facial Animation through A Unified Model","created":"2024-08-01","cited_by_count":30},{"id":"2409.18127","title":"EgoLM: Multi-Modal Language Model of Egocentric Motions","created":"2024-09-26","cited_by_count":28},{"id":"2408.02879","title":"Body of Her: A Preliminary Study on End-to-End Humanoid Agent","created":"2024-08-06","cited_by_count":15}],"next_cursor":null}