{"total":629,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863,"area":"diffusion"},{"id":"2405.09818","title":"Chameleon: Mixed-Modal Early-Fusion Foundation Models","created":"2024-05-16","cited_by_count":927,"area":null},{"id":"2309.16588","title":"Vision Transformers Need Registers","created":"2023-09-28","cited_by_count":871,"area":null},{"id":"2506.09985","title":"V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning","created":"2025-06-11","cited_by_count":809,"area":"wm"},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808,"area":"agents"},{"id":"2202.03052","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","created":"2022-02-07","cited_by_count":745,"area":null},{"id":"2202.03555","title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","created":"2022-02-07","cited_by_count":727,"area":null},{"id":"2306.13643","title":"LightGlue: Local Feature Matching at Light Speed","created":"2023-06-23","cited_by_count":590,"area":null},{"id":"2209.05451","title":"Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation","created":"2022-09-12","cited_by_count":551,"area":null},{"id":"2307.07635","title":"CoTracker: It is Better to Track Together","created":"2023-07-14","cited_by_count":522,"area":null},{"id":"2405.17428","title":"NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models","created":"2024-05-27","cited_by_count":472,"area":null},{"id":"2203.06604","title":"Masked Autoencoders for Point Cloud Self-supervised Learning","created":"2022-03-13","cited_by_count":459,"area":null},{"id":"2206.08916","title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","created":"2022-06-17","cited_by_count":421,"area":null},{"id":"2210.03094","title":"VIMA: General Robot Manipulation with Multimodal Prompts","created":"2022-10-06","cited_by_count":407,"area":null},{"id":"2410.02073","title":"Depth Pro: Sharp Monocular Metric Depth in Less Than a Second","created":"2024-10-02","cited_by_count":404,"area":null},{"id":"2111.13680","title":"GMFlow: Learning Optical Flow via Global Matching","created":"2021-11-26","cited_by_count":327,"area":null},{"id":"2212.02499","title":"Images Speak in Images: A Generalist Painter for In-Context Visual Learning","created":"2022-12-05","cited_by_count":318,"area":null},{"id":"2305.13786","title":"Perception Test: A Diagnostic Benchmark for Multimodal Video Models","created":"2023-05-23","cited_by_count":314,"area":"lr"},{"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":"2111.11326","title":"DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion","created":"2021-11-22","cited_by_count":291,"area":null},{"id":"2204.01678","title":"MultiMAE: Multi-modal Multi-task Masked Autoencoders","created":"2022-04-04","cited_by_count":291,"area":null},{"id":"2207.05844","title":"Wayformer: Motion Forecasting via Simple & Efficient Attention Networks","created":"2022-07-12","cited_by_count":280,"area":"wm"},{"id":"2405.14093","title":"A Survey on Vision-Language-Action Models for Embodied AI","created":"2024-05-23","cited_by_count":279,"area":"vla"},{"id":"2203.16194","title":"FlowFormer: A Transformer Architecture for Optical Flow","created":"2022-03-30","cited_by_count":275,"area":null},{"id":"2211.05783","title":"Unifying Flow, Stereo and Depth Estimation","created":"2022-11-10","cited_by_count":275,"area":null},{"id":"2111.12594","title":"Conditional Object-Centric Learning from Video","created":"2021-11-24","cited_by_count":248,"area":"wm"},{"id":"2310.01957","title":"Driving with LLMs: Fusing Object-Level Vector Modality for Explainable Autonomous Driving","created":"2023-10-03","cited_by_count":232,"area":"driving"},{"id":"2209.14860","title":"Bridging the Gap to Real-World Object-Centric Learning","created":"2022-09-29","cited_by_count":220,"area":null},{"id":"2312.00785","title":"Sequential Modeling Enables Scalable Learning for Large Vision Models","created":"2023-12-01","cited_by_count":212,"area":null},{"id":"2207.06881","title":"Recurrent Memory Transformer","created":"2022-07-14","cited_by_count":203,"area":null},{"id":"2212.11972","title":"Scalable Adaptive Computation for Iterative Generation","created":"2022-12-22","cited_by_count":195,"area":"diffusion"},{"id":"2410.17242","title":"LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias","created":"2024-10-22","cited_by_count":189,"area":null},{"id":"2207.02505","title":"Pure Transformers are Powerful Graph Learners","created":"2022-07-06","cited_by_count":188,"area":null},{"id":"2201.12204","title":"From data to functa: Your data point is a function and you can treat it like one","created":"2022-01-28","cited_by_count":187,"area":null},{"id":"2404.04319","title":"SpatialTracker: Tracking Any 2D Pixels in 3D Space","created":"2024-04-05","cited_by_count":181,"area":null},{"id":"2512.14692","title":"Native and Compact Structured Latents for 3D Generation","created":"2025-12-16","cited_by_count":175,"area":null},{"id":"2206.07669","title":"A Unified Sequence Interface for Vision Tasks","created":"2022-06-15","cited_by_count":152,"area":null},{"id":"2201.04288","title":"Multiview Transformers for Video Recognition","created":"2022-01-12","cited_by_count":148,"area":null},{"id":"2206.06565","title":"LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks","created":"2022-06-14","cited_by_count":148,"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":"2110.10090","title":"Inductive Biases and Variable Creation in Self-Attention Mechanisms","created":"2021-10-19","cited_by_count":144,"area":null},{"id":"2206.03428","title":"Revealing Single Frame Bias for Video-and-Language Learning","created":"2022-06-07","cited_by_count":133,"area":null},{"id":"2204.08451","title":"Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion","created":"2022-04-18","cited_by_count":126,"area":null},{"id":"2211.10277","title":"Task Residual for Tuning Vision-Language Models","created":"2022-11-18","cited_by_count":123,"area":"mllm"},{"id":"2312.06647","title":"4M: Massively Multimodal Masked Modeling","created":"2023-12-11","cited_by_count":120,"area":null},{"id":"2203.05328","title":"Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking","created":"2022-03-10","cited_by_count":119,"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":"2306.01923","title":"The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation","created":"2023-06-02","cited_by_count":116,"area":"diffusion"},{"id":"2303.01237","title":"FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation","created":"2023-03-02","cited_by_count":114,"area":null},{"id":"2203.10833","title":"Hyperbolic Vision Transformers: Combining Improvements in Metric Learning","created":"2022-03-21","cited_by_count":111,"area":null},{"id":"2212.07525","title":"Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language","created":"2022-12-14","cited_by_count":110,"area":null},{"id":"2109.10686","title":"Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers","created":"2021-09-22","cited_by_count":106,"area":null},{"id":"2308.08708","title":"Consciousness in Artificial Intelligence: Insights from the Science of Consciousness","created":"2023-08-17","cited_by_count":104,"area":null},{"id":"2306.17253","title":"Towards Zero-Shot Scale-Aware Monocular Depth Estimation","created":"2023-06-29","cited_by_count":101,"area":null},{"id":"2110.12894","title":"The Efficiency Misnomer","created":"2021-10-25","cited_by_count":98,"area":null},{"id":"2206.06336","title":"Language Models are General-Purpose Interfaces","created":"2022-06-13","cited_by_count":97,"area":null},{"id":"2403.03890","title":"Hierarchical Diffusion Policy for Kinematics-Aware Multi-Task Robotic Manipulation","created":"2024-03-06","cited_by_count":93,"area":"diffusion"},{"id":"2304.06819","title":"Modeling Dense Multimodal Interactions Between Biological Pathways and Histology for Survival Prediction","created":"2023-04-13","cited_by_count":92,"area":null},{"id":"2205.00823","title":"CenterCLIP: Token Clustering for Efficient Text-Video Retrieval","created":"2022-05-02","cited_by_count":86,"area":null},{"id":"2310.17722","title":"Large Language Models as Generalizable Policies for Embodied Tasks","created":"2023-10-26","cited_by_count":86,"area":null},{"id":"2203.16896","title":"CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow","created":"2022-03-31","cited_by_count":82,"area":null},{"id":"2301.03313","title":"BQ-NCO: Bisimulation Quotienting for Efficient Neural Combinatorial Optimization","created":"2023-01-09","cited_by_count":82,"area":null},{"id":"2303.08340","title":"VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation","created":"2023-03-15","cited_by_count":82,"area":null},{"id":"2204.09443","title":"GIMO: Gaze-Informed Human Motion Prediction in Context","created":"2022-04-20","cited_by_count":81,"area":null},{"id":"2411.04954","title":"CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLM","created":"2024-11-07","cited_by_count":81,"area":null},{"id":"2403.18036","title":"Move as You Say, Interact as You Can: Language-guided Human Motion Generation with Scene Affordance","created":"2024-03-26","cited_by_count":80,"area":"diffusion"},{"id":"2506.07961","title":"BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models","created":"2025-06-09","cited_by_count":80,"area":"mllm"},{"id":"2112.04446","title":"Everything at Once -- Multi-modal Fusion Transformer for Video Retrieval","created":"2021-12-08","cited_by_count":79,"area":null},{"id":"2205.10337","title":"UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes","created":"2022-05-20","cited_by_count":78,"area":null},{"id":"2306.13653","title":"ProRes: Exploring Degradation-aware Visual Prompt for Universal Image Restoration","created":"2023-06-23","cited_by_count":77,"area":null},{"id":"2301.10222","title":"RangeViT: Towards Vision Transformers for 3D Semantic Segmentation in Autonomous Driving","created":"2023-01-24","cited_by_count":76,"area":null},{"id":"2111.12701","title":"Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes","created":"2021-11-24","cited_by_count":71,"area":"diffusion"},{"id":"2301.08247","title":"Multiview Compressive Coding for 3D Reconstruction","created":"2023-01-19","cited_by_count":71,"area":null},{"id":"2405.11442","title":"Unifying 3D Vision-Language Understanding via Promptable Queries","created":"2024-05-19","cited_by_count":70,"area":null},{"id":"2304.04321","title":"ARNOLD: A Benchmark for Language-Grounded Task Learning With Continuous States in Realistic 3D Scenes","created":"2023-04-09","cited_by_count":69,"area":null},{"id":"2202.12015","title":"Learning to Merge Tokens in Vision Transformers","created":"2022-02-24","cited_by_count":65,"area":null},{"id":"2307.04722","title":"Advances and Challenges in Meta-Learning: A Technical Review","created":"2023-07-10","cited_by_count":65,"area":null},{"id":"2310.18308","title":"Gen2Sim: Scaling up Robot Learning in Simulation with Generative Models","created":"2023-10-27","cited_by_count":64,"area":null},{"id":"2304.05366","title":"The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning","created":"2023-04-11","cited_by_count":63,"area":null},{"id":"2407.21770","title":"MoMa: Efficient Early-Fusion Pre-training with Mixture of Modality-Aware Experts","created":"2024-07-31","cited_by_count":62,"area":"moe"},{"id":"2412.18608","title":"PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Models","created":"2024-12-24","cited_by_count":62,"area":"diffusion"},{"id":"2310.16046","title":"A Unified, Scalable Framework for Neural Population Decoding","created":"2023-10-24","cited_by_count":61,"area":null},{"id":"2312.00786","title":"Dense Optical Tracking: Connecting the Dots","created":"2023-12-01","cited_by_count":61,"area":null},{"id":"2402.05741","title":"Real-World Robot Applications of Foundation Models: A Review","created":"2024-02-08","cited_by_count":61,"area":"mllm"},{"id":"2202.07765","title":"General-purpose, long-context autoregressive modeling with Perceiver AR","created":"2022-02-15","cited_by_count":60,"area":null},{"id":"2210.08990","title":"Improving Object-centric Learning with Query Optimization","created":"2022-10-17","cited_by_count":60,"area":null},{"id":"2111.12993","title":"PolyViT: Co-training Vision Transformers on Images, Videos and Audio","created":"2021-11-25","cited_by_count":58,"area":null},{"id":"2311.17932","title":"Swallowing the Bitter Pill: Simplified Scalable Conformer Generation","created":"2023-11-27","cited_by_count":56,"area":"diffusion"},{"id":"2212.08045","title":"CLIPPO: Image-and-Language Understanding from Pixels Only","created":"2022-12-15","cited_by_count":55,"area":null},{"id":"2404.04808","title":"MemFlow: Optical Flow Estimation and Prediction with Memory","created":"2024-04-07","cited_by_count":55,"area":null},{"id":"2301.02229","title":"All in Tokens: Unifying Output Space of Visual Tasks via Soft Token","created":"2023-01-05","cited_by_count":52,"area":null},{"id":"2304.14933","title":"An Empirical Study of Multimodal Model Merging","created":"2023-04-28","cited_by_count":52,"area":null},{"id":"2403.12943","title":"Vid2Robot: End-to-end Video-conditioned Policy Learning with Cross-Attention Transformers","created":"2024-03-19","cited_by_count":52,"area":null},{"id":"2204.03355","title":"Event Transformer. A sparse-aware solution for efficient event data processing","created":"2022-04-07","cited_by_count":50,"area":null},{"id":"2211.13672","title":"A Self-Attention Ansatz for Ab-initio Quantum Chemistry","created":"2022-11-24","cited_by_count":49,"area":null},{"id":"2212.03229","title":"Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning","created":"2022-12-06","cited_by_count":49,"area":null},{"id":"2212.05922","title":"Audiovisual Masked Autoencoders","created":"2022-12-09","cited_by_count":49,"area":null},{"id":"2502.00806","title":"UniGraph2: Learning a Unified Embedding Space to Bind Multimodal Graphs","created":"2025-02-02","cited_by_count":49,"area":"moe"},{"id":"2503.20853","title":"Unified Multimodal Discrete Diffusion","created":"2025-03-26","cited_by_count":49,"area":"diffusion"},{"id":"2303.18230","title":"Procedure-Aware Pretraining for Instructional Video Understanding","created":"2023-03-31","cited_by_count":48,"area":null}],"next_cursor":"100"}