{"total":869,"rows":[{"id":"2311.04400","title":"LRM: Large Reconstruction Model for Single Image to 3D","created":"2023-11-08","cited_by_count":849,"area":null},{"id":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","cited_by_count":771,"area":null},{"id":"2306.08302","title":"Unifying Large Language Models and Knowledge Graphs: A Roadmap","created":"2023-06-14","cited_by_count":668,"area":null},{"id":"2308.10792","title":"Instruction Tuning for Large Language Models: A Survey","created":"2023-08-21","cited_by_count":623,"area":null},{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542,"area":null},{"id":"2306.14795","title":"MotionGPT: Human Motion as a Foreign Language","created":"2023-06-26","cited_by_count":527,"area":null},{"id":"2402.19479","title":"Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers","created":"2024-02-29","cited_by_count":393,"area":null},{"id":"2310.01852","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","created":"2023-10-03","cited_by_count":370,"area":null},{"id":"2305.16355","title":"PandaGPT: One Model To Instruction-Follow Them All","created":"2023-05-25","cited_by_count":334,"area":null},{"id":"2308.16911","title":"PointLLM: Empowering Large Language Models to Understand Point Clouds","created":"2023-08-31","cited_by_count":333,"area":null},{"id":"2307.03601","title":"GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest","created":"2023-07-07","cited_by_count":302,"area":null},{"id":"2312.17172","title":"Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action","created":"2023-12-28","cited_by_count":302,"area":null},{"id":"2306.13631","title":"OpenMask3D: Open-Vocabulary 3D Instance Segmentation","created":"2023-06-23","cited_by_count":289,"area":null},{"id":"2311.01455","title":"RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation","created":"2023-11-02","cited_by_count":218,"area":null},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"area":null},{"id":"2309.00615","title":"Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following","created":"2023-09-01","cited_by_count":194,"area":null},{"id":"2407.06886","title":"Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI","created":"2024-07-09","cited_by_count":179,"area":null},{"id":"2406.16964","title":"Are Language Models Actually Useful for Time Series Forecasting?","created":"2024-06-22","cited_by_count":168,"area":null},{"id":"2311.17136","title":"UniIR: Training and Benchmarking Universal Multimodal Information Retrievers","created":"2023-11-28","cited_by_count":166,"area":null},{"id":"2409.20537","title":"Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformers","created":"2024-09-30","cited_by_count":148,"area":null},{"id":"2407.06358","title":"MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions","created":"2024-07-08","cited_by_count":146,"area":null},{"id":"2309.03905","title":"ImageBind-LLM: Multi-modality Instruction Tuning","created":"2023-09-07","cited_by_count":142,"area":null},{"id":"2307.10802","title":"Meta-Transformer: A Unified Framework for Multimodal Learning","created":"2023-07-20","cited_by_count":136,"area":null},{"id":"2412.15322","title":"MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis","created":"2024-12-19","cited_by_count":134,"area":null},{"id":"2401.10815","title":"Exploring scalable medical image encoders beyond text supervision","created":"2024-01-19","cited_by_count":132,"area":null},{"id":"2312.06647","title":"4M: Massively Multimodal Masked Modeling","created":"2023-12-11","cited_by_count":120,"area":null},{"id":"2305.11172","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","created":"2023-05-18","cited_by_count":118,"area":null},{"id":"2402.01801","title":"Large Language Models for Time Series: A Survey","created":"2024-02-02","cited_by_count":114,"area":null},{"id":"2402.17723","title":"Seeing and Hearing: Open-domain Visual-Audio Generation with Diffusion Latent Aligners","created":"2024-02-27","cited_by_count":111,"area":null},{"id":"2307.13721","title":"Foundational Models Defining a New Era in Vision: A Survey and Outlook","created":"2023-07-25","cited_by_count":110,"area":null},{"id":"2407.01494","title":"FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds","created":"2024-07-01","cited_by_count":110,"area":null},{"id":"2311.18809","title":"FoundPose: Unseen Object Pose Estimation with Foundation Features","created":"2023-11-30","cited_by_count":109,"area":null},{"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,"area":null},{"id":"2402.13217","title":"VideoPrism: A Foundational Visual Encoder for Video Understanding","created":"2024-02-20","cited_by_count":105,"area":null},{"id":"2312.08782","title":"Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis","created":"2023-12-14","cited_by_count":103,"area":null},{"id":"2406.15704","title":"video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models","created":"2024-06-22","cited_by_count":102,"area":null},{"id":"2309.09510","title":"Dynamic-SUPERB: Towards A Dynamic, Collaborative, and Comprehensive Instruction-Tuning Benchmark for Speech","created":"2023-09-18","cited_by_count":101,"area":null},{"id":"2410.10818","title":"TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models","created":"2024-10-14","cited_by_count":97,"area":null},{"id":"2312.12359","title":"CLIP-DINOiser: Teaching CLIP a few DINO tricks for open-vocabulary semantic segmentation","created":"2023-12-19","cited_by_count":96,"area":null},{"id":"2312.05409","title":"Large-scale Training of Foundation Models for Wearable Biosignals","created":"2023-12-08","cited_by_count":95,"area":null},{"id":"2401.18084","title":"Binding Touch to Everything: Learning Unified Multimodal Tactile Representations","created":"2024-01-31","cited_by_count":95,"area":null},{"id":"2409.07825","title":"Deep Multimodal Learning with Missing Modality: A Survey","created":"2024-09-12","cited_by_count":92,"area":null},{"id":"2307.11067","title":"CNOS: A Strong Baseline for CAD-based Novel Object Segmentation","created":"2023-07-20","cited_by_count":87,"area":null},{"id":"2404.01014","title":"Harnessing Large Language Models for Training-free Video Anomaly Detection","created":"2024-04-01","cited_by_count":87,"area":null},{"id":"2308.07123","title":"An Outlook into the Future of Egocentric Vision","created":"2023-08-14","cited_by_count":84,"area":null},{"id":"2504.08685","title":"Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model","created":"2025-04-11","cited_by_count":82,"area":null},{"id":"2402.12259","title":"Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships","created":"2024-02-19","cited_by_count":80,"area":null},{"id":"2510.15742","title":"Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset","created":"2025-10-17","cited_by_count":79,"area":null},{"id":"2308.11276","title":"Music Understanding LLaMA: Advancing Text-to-Music Generation with Question Answering and Captioning","created":"2023-08-22","cited_by_count":77,"area":null},{"id":"2402.13598","title":"User-LLM: Efficient LLM Contextualization with User Embeddings","created":"2024-02-21","cited_by_count":76,"area":null},{"id":"2406.18522","title":"ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation","created":"2024-06-26","cited_by_count":75,"area":null},{"id":"2411.17040","title":"Multimodal Alignment and Fusion: A Survey","created":"2024-11-26","cited_by_count":74,"area":null},{"id":"2404.17176","title":"MovieChat+: Question-aware Sparse Memory for Long Video Question Answering","created":"2024-04-26","cited_by_count":73,"area":null},{"id":"2402.13232","title":"A Touch, Vision, and Language Dataset for Multimodal Alignment","created":"2024-02-20","cited_by_count":69,"area":null},{"id":"2310.00230","title":"SLM: Bridge the thin gap between speech and text foundation models","created":"2023-09-30","cited_by_count":67,"area":null},{"id":"2305.16103","title":"ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst","created":"2023-05-25","cited_by_count":66,"area":null},{"id":"2311.15851","title":"Single-Model and Any-Modality for Video Object Tracking","created":"2023-11-27","cited_by_count":65,"area":null},{"id":"2404.01284","title":"Large Motion Model for Unified Multi-Modal Motion Generation","created":"2024-04-01","cited_by_count":65,"area":null},{"id":"2305.08196","title":"A Comprehensive Survey on Segment Anything Model for Vision and Beyond","created":"2023-05-14","cited_by_count":64,"area":null},{"id":"2310.09605","title":"Penetrative AI: Making LLMs Comprehend the Physical World","created":"2023-10-14","cited_by_count":64,"area":null},{"id":"2311.15599","title":"UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition","created":"2023-11-27","cited_by_count":64,"area":null},{"id":"2404.08351","title":"OmniSat: Self-Supervised Modality Fusion for Earth Observation","created":"2024-04-12","cited_by_count":63,"area":null},{"id":"2510.15870","title":"OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM","created":"2025-10-17","cited_by_count":59,"area":null},{"id":"2404.00579","title":"A Review of Modern Recommender Systems Using Generative Models (Gen-RecSys)","created":"2024-03-31","cited_by_count":58,"area":null},{"id":"2312.00947","title":"FreeZe: Training-free zero-shot 6D pose estimation with geometric and vision foundation models","created":"2023-12-01","cited_by_count":57,"area":null},{"id":"2410.18325","title":"AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language Models","created":"2024-10-23","cited_by_count":56,"area":null},{"id":"2311.17404","title":"VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models","created":"2023-11-29","cited_by_count":55,"area":null},{"id":"2403.14622","title":"Language Repository for Long Video Understanding","created":"2024-03-21","cited_by_count":55,"area":null},{"id":"2505.12540","title":"Harnessing the Universal Geometry of Embeddings","created":"2025-05-18","cited_by_count":55,"area":null},{"id":"2412.11959","title":"Gramian Multimodal Representation Learning and Alignment","created":"2024-12-16","cited_by_count":54,"area":null},{"id":"2406.09406","title":"4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities","created":"2024-06-13","cited_by_count":52,"area":null},{"id":"2409.13689","title":"Temporally Aligned Audio for Video with Autoregression","created":"2024-09-20","cited_by_count":52,"area":null},{"id":"2312.14556","title":"CaptainCook4D: A Dataset for Understanding Errors in Procedural Activities","created":"2023-12-22","cited_by_count":51,"area":null},{"id":"2411.19772","title":"LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos","created":"2024-11-29","cited_by_count":51,"area":null},{"id":"2312.08963","title":"LEMON: Learning 3D Human-Object Interaction Relation from 2D Images","created":"2023-12-14","cited_by_count":49,"area":null},{"id":"2403.12532","title":"UniBind: LLM-Augmented Unified and Balanced Representation Space to Bind Them All","created":"2024-03-19","cited_by_count":49,"area":null},{"id":"2411.17698","title":"Video-Guided Foley Sound Generation with Multimodal Controls","created":"2024-11-26","cited_by_count":49,"area":null},{"id":"2407.05551","title":"Read, Watch and Scream! Sound Generation from Text and Video","created":"2024-07-08","cited_by_count":48,"area":null},{"id":"2502.12191","title":"AnyTouch: Learning Unified Static-Dynamic Representation across Multiple Visuo-tactile Sensors","created":"2025-02-15","cited_by_count":48,"area":null},{"id":"2406.13640","title":"Transferable Tactile Transformers for Representation Learning Across Diverse Sensors and Tasks","created":"2024-06-19","cited_by_count":45,"area":null},{"id":"2409.18042","title":"EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions","created":"2024-09-26","cited_by_count":45,"area":null},{"id":"2312.11541","title":"CLIPSyntel: CLIP and LLM Synergy for Multimodal Question Summarization in Healthcare","created":"2023-12-16","cited_by_count":43,"area":null},{"id":"2602.08794","title":"MOVA: Towards Scalable and Synchronized Video-Audio Generation","created":"2026-02-09","cited_by_count":43,"area":null},{"id":"2310.03185","title":"Misusing Tools in Large Language Models With Visual Adversarial Examples","created":"2023-10-04","cited_by_count":42,"area":null},{"id":"2306.09126","title":"STARSS23: An Audio-Visual Dataset of Spatial Recordings of Real Scenes with Spatiotemporal Annotations of Sound Events","created":"2023-06-15","cited_by_count":41,"area":null},{"id":"2309.15785","title":"BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning","created":"2023-09-27","cited_by_count":41,"area":null},{"id":"2311.00926","title":"M2T2: Multi-Task Masked Transformer for Object-centric Pick and Place","created":"2023-11-02","cited_by_count":41,"area":null},{"id":"2406.04321","title":"VidMuse: A Simple Video-to-Music Generation Framework with Long-Short-Term Modeling","created":"2024-06-06","cited_by_count":40,"area":null},{"id":"2401.08577","title":"MultiPLY: A Multisensory Object-Centric Embodied Large Language Model in 3D World","created":"2024-01-16","cited_by_count":39,"area":null},{"id":"2407.11895","title":"OmniBind: Large-scale Omni Multimodal Representation via Binding Spaces","created":"2024-07-16","cited_by_count":39,"area":null},{"id":"2403.01988","title":"FKA-Owl: Advancing Multimodal Fake News Detection through Knowledge-Augmented LVLMs","created":"2024-03-04","cited_by_count":38,"area":null},{"id":"2312.00937","title":"Zero-Shot Video Question Answering with Procedural Programs","created":"2023-12-01","cited_by_count":37,"area":null},{"id":"2309.05300","title":"Decoupling Common and Unique Representations for Multimodal Self-supervised Learning","created":"2023-09-11","cited_by_count":36,"area":null},{"id":"2404.14412","title":"AutoAD III: The Prequel -- Back to the Pixels","created":"2024-04-22","cited_by_count":35,"area":null},{"id":"2407.13761","title":"SegPoint: Segment Any Point Cloud via Large Language Model","created":"2024-07-18","cited_by_count":35,"area":null},{"id":"2411.00683","title":"TaxaBind: A Unified Embedding Space for Ecological Applications","created":"2024-11-01","cited_by_count":35,"area":null},{"id":"2512.10945","title":"MeViS: A Multi-Modal Dataset for Referring Motion Expression Video Segmentation","created":"2025-12-11","cited_by_count":35,"area":null},{"id":"2309.06236","title":"The first step is the hardest: Pitfalls of Representing and Tokenizing Temporal Data for Large Language Models","created":"2023-09-12","cited_by_count":34,"area":null},{"id":"2404.03635","title":"WorDepth: Variational Language Prior for Monocular Depth Estimation","created":"2024-04-04","cited_by_count":34,"area":null},{"id":"2404.03214","title":"LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity","created":"2024-04-04","cited_by_count":33,"area":null}],"next_cursor":"100"}