{"list":"other","total":115,"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":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120},{"id":"2308.00352","title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","created":"2023-08-01","cited_by_count":1808},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"2405.21075","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","created":"2024-05-31","cited_by_count":1413},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"id":"2306.05424","title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","created":"2023-06-08","cited_by_count":1062},{"id":"2404.16821","title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","created":"2024-04-25","cited_by_count":1050},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744},{"id":"2312.07533","title":"VILA: On Pre-training for Visual Language Models","created":"2023-12-12","cited_by_count":692},{"id":"2308.09126","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","created":"2023-08-17","cited_by_count":680},{"id":"2407.15754","title":"LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding","created":"2024-07-22","cited_by_count":665},{"id":"2308.10848","title":"AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors","created":"2023-08-21","cited_by_count":598},{"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":"1906.02467","title":"ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering","created":"2019-06-06","cited_by_count":561},{"id":"2311.17043","title":"LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models","created":"2023-11-28","cited_by_count":546},{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542},{"id":"1612.00222","title":"Interaction Networks for Learning about Objects, Relations and Physics","created":"2016-12-01","cited_by_count":509},{"id":"1910.01442","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","created":"2019-10-03","cited_by_count":484},{"id":"2210.13382","title":"Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task","created":"2022-10-24","cited_by_count":431},{"id":"1806.07011","title":"VirtualHome: Simulating Household Activities via Programs","created":"2018-06-19","cited_by_count":415},{"id":"2406.08035","title":"LVBench: An Extreme Long Video Understanding Benchmark","created":"2024-06-12","cited_by_count":410},{"id":"1704.04497","title":"TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering","created":"2017-04-14","cited_by_count":378},{"id":"2311.08046","title":"Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding","created":"2023-11-14","cited_by_count":371},{"id":"2403.00476","title":"TempCompass: Do Video LLMs Really Understand Videos?","created":"2024-03-01","cited_by_count":363},{"id":"2005.00200","title":"HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training","created":"2020-05-01","cited_by_count":362},{"id":"1910.05789","title":"On the Utility of Learning about Humans for Human-AI Coordination","created":"2019-10-13","cited_by_count":349},{"id":"2305.13786","title":"Perception Test: A Diagnostic Benchmark for Multimodal Video Models","created":"2023-05-23","cited_by_count":314},{"id":"1605.07157","title":"Unsupervised Learning for Physical Interaction through Video Prediction","created":"2016-05-23","cited_by_count":260},{"id":"2007.04954","title":"ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulation","created":"2020-07-09","cited_by_count":250},{"id":"2406.03520","title":"VideoPhy: Evaluating Physical Commonsense for Video Generation","created":"2024-06-05","cited_by_count":228},{"id":"2405.09711","title":"STAR: A Benchmark for Situated Reasoning in Real-World Videos","created":"2024-05-15","cited_by_count":213},{"id":"2410.05363","title":"Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation","created":"2024-10-07","cited_by_count":174},{"id":"1606.07419","title":"Learning to Poke by Poking: Experiential Learning of Intuitive Physics","created":"2016-06-23","cited_by_count":154},{"id":"2106.08261","title":"Physion: Evaluating Physical Prediction from Vision in Humans and Machines","created":"2021-06-15","cited_by_count":153},{"id":"2404.01258","title":"Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward","created":"2024-04-01","cited_by_count":147},{"id":"1710.05268","title":"Self-Supervised Visual Planning with Temporal Skip Connections","created":"2017-10-15","cited_by_count":139},{"id":"1910.04744","title":"CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning","created":"2019-10-10","cited_by_count":137},{"id":"2010.09890","title":"Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration","created":"2020-10-19","cited_by_count":133},{"id":"2404.00308","title":"ST-LLM: Large Language Models Are Effective Temporal Learners","created":"2024-03-30","cited_by_count":126},{"id":"1612.00341","title":"A Compositional Object-Based Approach to Learning Physical Dynamics","created":"2016-12-01","cited_by_count":119},{"id":"2404.02039","title":"A Survey on Large Language Model-Based Game Agents","created":"2024-04-02","cited_by_count":112},{"id":"2311.16103","title":"Video-Bench: A Comprehensive Benchmark and Toolkit for Evaluating Video-based Large Language Models","created":"2023-11-27","cited_by_count":107},{"id":"2310.01320","title":"Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplation","created":"2023-10-02","cited_by_count":104},{"id":"2402.03161","title":"Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization","created":"2024-02-05","cited_by_count":100},{"id":"1706.01433","title":"Visual Interaction Networks","created":"2017-06-05","cited_by_count":95},{"id":"2402.17574","title":"Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization","created":"2024-02-27","cited_by_count":94},{"id":"2310.19773","title":"MM-VID: Advancing Video Understanding with GPT-4V(ision)","created":"2023-10-30","cited_by_count":83},{"id":"1909.12000","title":"CoPhy: Counterfactual Learning of Physical Dynamics","created":"2019-09-26","cited_by_count":81},{"id":"2312.11865","title":"Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization Approach","created":"2023-12-19","cited_by_count":79},{"id":"2306.09200","title":"ChessGPT: Bridging Policy Learning and Language Modeling","created":"2023-06-15","cited_by_count":75},{"id":"2102.13249","title":"Chess as a Testbed for Language Model State Tracking","created":"2021-02-26","cited_by_count":72},{"id":"2409.18111","title":"E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding","created":"2024-09-26","cited_by_count":70},{"id":"2103.16392","title":"CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive Learning","created":"2021-03-30","cited_by_count":69},{"id":"1603.01312","title":"Learning Physical Intuition of Block Towers by Example","created":"2016-03-03","cited_by_count":68},{"id":"2309.17277","title":"Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4","created":"2023-09-29","cited_by_count":68},{"id":"2103.14025","title":"The ThreeDWorld Transport Challenge: A Visually Guided Task-and-Motion Planning Benchmark for Physically Realistic Embodied AI","created":"2021-03-25","cited_by_count":65},{"id":"2310.17956","title":"Qilin-Med-VL: Towards Chinese Large Vision-Language Model for General Healthcare","created":"2023-10-27","cited_by_count":62},{"id":"1511.07404","title":"Learning Visual Predictive Models of Physics for Playing Billiards","created":"2015-11-23","cited_by_count":58},{"id":"2311.17404","title":"VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models","created":"2023-11-29","cited_by_count":55},{"id":"2109.06085","title":"On Pursuit of Designing Multi-modal Transformer for Video Grounding","created":"2021-09-13","cited_by_count":54},{"id":"2306.15668","title":"Physion++: Evaluating Physical Scene Understanding that Requires Online Inference of Different Physical Properties","created":"2023-06-27","cited_by_count":54},{"id":"2311.13435","title":"PG-Video-LLaVA: Pixel Grounding Large Video-Language Models","created":"2023-11-22","cited_by_count":51},{"id":"2312.15224","title":"LLM-Powered Hierarchical Language Agent for Real-time Human-AI Coordination","created":"2023-12-23","cited_by_count":48},{"id":"2012.04293","title":"CRAFT: A Benchmark for Causal Reasoning About Forces and inTeractions","created":"2020-12-08","cited_by_count":44},{"id":"2207.10362","title":"LocVTP: Video-Text Pre-training for Temporal Localization","created":"2022-07-21","cited_by_count":44},{"id":"2311.14906","title":"AutoEval-Video: An Automatic Benchmark for Assessing Large Vision Language Models in Open-Ended Video Question Answering","created":"2023-11-25","cited_by_count":40},{"id":"2410.17594","title":"How to Continually Adapt Text-to-Image Diffusion Models for Flexible Customization?","created":"2024-10-23","cited_by_count":33},{"id":"2203.13609","title":"Unsupervised Pre-training for Temporal Action Localization Tasks","created":"2022-03-25","cited_by_count":31},{"id":"2404.02845","title":"Cross-Modal Conditioned Reconstruction for Language-guided Medical Image Segmentation","created":"2024-04-03","cited_by_count":28},{"id":"2310.09089","title":"Qilin-Med: Multi-stage Knowledge Injection Advanced Medical Large Language Model","created":"2023-10-13","cited_by_count":24},{"id":"1603.05600","title":"\"What happens if...\" Learning to Predict the Effect of Forces in Images","created":"2016-03-17","cited_by_count":23},{"id":"2312.05291","title":"GlitchBench: Can large multimodal models detect video game glitches?","created":"2023-12-08","cited_by_count":23},{"id":"2402.04578","title":"S-Agents: Self-organizing Agents in Open-ended Environments","created":"2024-02-07","cited_by_count":22},{"id":"2403.10249","title":"A Survey on Game Playing Agents and Large Models: Methods, Applications, and Challenges","created":"2024-03-15","cited_by_count":22},{"id":"2411.02564","title":"Continual LLaVA: Continual Instruction Tuning in Large Vision-Language Models","created":"2024-11-04","cited_by_count":22},{"id":"2307.14277","title":"G2L: Semantically Aligned and Uniform Video Grounding via Geodesic and Game Theory","created":"2023-07-26","cited_by_count":21},{"id":"2406.14129","title":"Towards Event-oriented Long Video Understanding","created":"2024-06-20","cited_by_count":21},{"id":"2308.12466","title":"Are ChatGPT and GPT-4 Good Poker Players? -- A Pre-Flop Analysis","created":"2023-08-23","cited_by_count":20},{"id":"2401.06781","title":"PokerGPT: An End-to-End Lightweight Solver for Multi-Player Texas Hold'em via Large Language Model","created":"2024-01-04","cited_by_count":20},{"id":"2411.02327","title":"PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance","created":"2024-11-04","cited_by_count":20},{"id":"1808.10002","title":"Interpretable Intuitive Physics Model","created":"2018-08-29","cited_by_count":19},{"id":"2401.17749","title":"SwarmBrain: Embodied agent for real-time strategy game StarCraft II via large language models","created":"2024-01-31","cited_by_count":19},{"id":"2405.19465","title":"RAP: Efficient Text-Video Retrieval with Sparse-and-Correlated Adapter","created":"2024-05-29","cited_by_count":16},{"id":"2203.11096","title":"CLIP meets GamePhysics: Towards bug identification in gameplay videos using zero-shot transfer learning","created":"2022-03-21","cited_by_count":15},{"id":"2210.02506","title":"Large Language Models are Pretty Good Zero-Shot Video Game Bug Detectors","created":"2022-10-05","cited_by_count":14},{"id":"2408.02687","title":"Compositional Physical Reasoning of Objects and Events from Videos","created":"2024-08-02","cited_by_count":12},{"id":"2108.05650","title":"UniFaceGAN: A Unified Framework for Temporally Consistent Facial Video Editing","created":"2021-08-12","cited_by_count":11}],"next_cursor":"100"}