{"total":871,"rows":[{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539,"area":null},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422,"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":"2404.15506","title":"Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation","created":"2024-03-22","cited_by_count":395,"area":null},{"id":"2405.02246","title":"What matters when building vision-language models?","created":"2024-05-03","cited_by_count":326,"area":"mllm"},{"id":"2504.13181","title":"Perception Encoder: The best visual embeddings are not at the output of the network","created":"2025-04-17","cited_by_count":326,"area":null},{"id":"2409.01652","title":"ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation","created":"2024-09-03","cited_by_count":315,"area":"lr"},{"id":"2510.11690","title":"Diffusion Transformers with Representation Autoencoders","created":"2025-10-13","cited_by_count":295,"area":"diffusion"},{"id":"2402.17762","title":"Massive Activations in Large Language Models","created":"2024-02-27","cited_by_count":294,"area":null},{"id":"2505.06708","title":"Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free","created":"2025-05-10","cited_by_count":283,"area":"moe"},{"id":"2310.02226","title":"Think before you speak: Training Language Models With Pause Tokens","created":"2023-10-03","cited_by_count":264,"area":"lr"},{"id":"2511.08544","title":"LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics","created":"2025-11-11","cited_by_count":254,"area":null},{"id":"2504.02792","title":"Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets","created":"2025-04-03","cited_by_count":240,"area":"wm"},{"id":"2601.03233","title":"LTX-2: Efficient Joint Audio-Visual Foundation Model","created":"2026-01-06","cited_by_count":236,"area":"diffusion"},{"id":"2505.23747","title":"Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence","created":"2025-05-29","cited_by_count":217,"area":"mllm"},{"id":"2410.10781","title":"When Attention Sink Emerges in Language Models: An Empirical View","created":"2024-10-14","cited_by_count":208,"area":"inference"},{"id":"2409.02095","title":"DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos","created":"2024-09-03","cited_by_count":204,"area":null},{"id":"2407.01449","title":"ColPali: Efficient Document Retrieval with Vision Language Models","created":"2024-06-27","cited_by_count":195,"area":"mllm"},{"id":"2407.21771","title":"Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs","created":"2024-07-31","cited_by_count":179,"area":"mllm"},{"id":"2404.08636","title":"Probing the 3D Awareness of Visual Foundation Models","created":"2024-04-12","cited_by_count":177,"area":null},{"id":"2502.17422","title":"MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs","created":"2025-02-24","cited_by_count":176,"area":"mllm"},{"id":"2408.12637","title":"Building and better understanding vision-language models: insights and future directions","created":"2024-08-22","cited_by_count":173,"area":"mllm"},{"id":"2408.00738","title":"Virchow2: Scaling Self-Supervised Mixed Magnification Models in Pathology","created":"2024-08-01","cited_by_count":161,"area":null},{"id":"2412.01818","title":"Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs","created":"2024-12-02","cited_by_count":157,"area":"mllm"},{"id":"2312.16272","title":"SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generation","created":"2023-12-26","cited_by_count":143,"area":null},{"id":"2509.24527","title":"Training Agents Inside of Scalable World Models","created":"2025-09-29","cited_by_count":136,"area":"wm"},{"id":"2503.03321","title":"See What You Are Told: Visual Attention Sink in Large Multimodal Models","created":"2025-03-05","cited_by_count":132,"area":"mllm"},{"id":"2511.08667","title":"TabPFN-2.5: Advancing the State of the Art in Tabular Foundation Models","created":"2025-11-11","cited_by_count":132,"area":null},{"id":"2410.07149","title":"Towards Interpreting Visual Information Processing in Vision-Language Models","created":"2024-10-09","cited_by_count":122,"area":"mllm"},{"id":"2410.15957","title":"CamI2V: Camera-Controlled Image-to-Video Diffusion Model","created":"2024-10-21","cited_by_count":120,"area":"diffusion"},{"id":"2603.14482","title":"V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning","created":"2026-03-15","cited_by_count":117,"area":null},{"id":"2410.06205","title":"Round and Round We Go! What makes Rotary Positional Encodings useful?","created":"2024-10-08","cited_by_count":115,"area":null},{"id":"2407.12442","title":"ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inference","created":"2024-07-17","cited_by_count":113,"area":"mllm"},{"id":"2408.04883","title":"ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation","created":"2024-08-09","cited_by_count":111,"area":null},{"id":"2503.16429","title":"Sonata: Self-Supervised Learning of Reliable Point Representations","created":"2025-03-20","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":"2411.13676","title":"Hymba: A Hybrid-head Architecture for Small Language Models","created":"2024-11-20","cited_by_count":99,"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":"2405.14325","title":"Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection","created":"2024-05-23","cited_by_count":93,"area":null},{"id":"2401.08559","title":"Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation","created":"2024-01-16","cited_by_count":91,"area":null},{"id":"2412.07679","title":"RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models","created":"2024-12-10","cited_by_count":89,"area":null},{"id":"2406.11430","title":"A Simple and Effective $L_2$ Norm-Based Strategy for KV Cache Compression","created":"2024-06-17","cited_by_count":86,"area":"inference"},{"id":"2405.00208","title":"A Primer on the Inner Workings of Transformer-based Language Models","created":"2024-04-30","cited_by_count":85,"area":null},{"id":"2412.16334","title":"DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment","created":"2024-12-20","cited_by_count":79,"area":null},{"id":"2502.12892","title":"Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models","created":"2025-02-18","cited_by_count":73,"area":"mechinterp"},{"id":"2406.01326","title":"TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy","created":"2024-06-03","cited_by_count":71,"area":null},{"id":"2407.20229","title":"Improving 2D Feature Representations by 3D-Aware Fine-Tuning","created":"2024-07-29","cited_by_count":71,"area":null},{"id":"2402.16846","title":"GROUNDHOG: Grounding Large Language Models to Holistic Segmentation","created":"2024-02-26","cited_by_count":70,"area":"mllm"},{"id":"2410.16499","title":"SINGAPO: Single Image Controlled Generation of Articulated Parts in Objects","created":"2024-10-21","cited_by_count":69,"area":null},{"id":"2410.11792","title":"OKAMI: Teaching Humanoid Robots Manipulation Skills through Single Video Imitation","created":"2024-10-15","cited_by_count":67,"area":null},{"id":"2412.17671","title":"A Bias-Free Training Paradigm for More General AI-generated Image Detection","created":"2024-12-23","cited_by_count":67,"area":"diffusion"},{"id":"2503.00710","title":"Proteina: Scaling Flow-based Protein Structure Generative Models","created":"2025-03-02","cited_by_count":65,"area":null},{"id":"2503.19108","title":"Your ViT is Secretly an Image Segmentation Model","created":"2025-03-24","cited_by_count":63,"area":null},{"id":"2502.03714","title":"Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment","created":"2025-02-06","cited_by_count":62,"area":"mechinterp"},{"id":"2407.08268","title":"Explore the Potential of CLIP for Training-Free Open Vocabulary Semantic Segmentation","created":"2024-07-11","cited_by_count":61,"area":"mllm"},{"id":"2407.20179","title":"Theia: Distilling Diverse Vision Foundation Models for Robot Learning","created":"2024-07-29","cited_by_count":61,"area":null},{"id":"2310.05707","title":"Guiding Language Model Reasoning with Planning Tokens","created":"2023-10-09","cited_by_count":58,"area":"lr"},{"id":"2507.19468","title":"Back to the Features: DINO as a Foundation for Video World Models","created":"2025-07-25","cited_by_count":58,"area":"wm"},{"id":"2410.13835","title":"Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs","created":"2024-10-17","cited_by_count":56,"area":null},{"id":"2508.15769","title":"SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass","created":"2025-08-21","cited_by_count":54,"area":null},{"id":"2502.04320","title":"ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features","created":"2025-02-06","cited_by_count":52,"area":"diffusion"},{"id":"2311.17137","title":"Generative Models: What Do They Know? Do They Know Things? Let's Find Out!","created":"2023-11-28","cited_by_count":50,"area":"diffusion"},{"id":"2405.15613","title":"Automatic Data Curation for Self-Supervised Learning: A Clustering-Based Approach","created":"2024-05-24","cited_by_count":50,"area":null},{"id":"2606.17846","title":"Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models","created":"2026-06-16","cited_by_count":50,"area":null},{"id":"2503.02424","title":"Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detection","created":"2025-03-04","cited_by_count":48,"area":null},{"id":"2502.01563","title":"Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding","created":"2025-02-03","cited_by_count":47,"area":null},{"id":"2410.01104","title":"Softmax is not Enough (for Sharp Size Generalisation)","created":"2024-10-01","cited_by_count":46,"area":null},{"id":"2412.11673","title":"DINO-Foresight: Looking into the Future with DINO","created":"2024-12-16","cited_by_count":45,"area":null},{"id":"2504.16064","title":"Boosting Generative Image Modeling via Joint Image-Feature Synthesis","created":"2025-04-22","cited_by_count":45,"area":"diffusion"},{"id":"2411.19331","title":"Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for Open-Vocabulary Segmentation","created":"2024-11-28","cited_by_count":44,"area":null},{"id":"2412.03439","title":"CleanDIFT: Diffusion Features without Noise","created":"2024-12-04","cited_by_count":44,"area":"diffusion"},{"id":"2505.21375","title":"GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution","created":"2025-05-27","cited_by_count":44,"area":"mllm"},{"id":"2511.21688","title":"G$^2$VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning","created":"2025-11-26","cited_by_count":44,"area":"lr"},{"id":"2601.05083","title":"Driving on Registers","created":"2026-01-08","cited_by_count":44,"area":"driving"},{"id":"2512.24497","title":"What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?","created":"2025-12-30","cited_by_count":43,"area":"wm"},{"id":"2401.04079","title":"RudolfV: A Foundation Model by Pathologists for Pathologists","created":"2024-01-08","cited_by_count":41,"area":null},{"id":"2403.17064","title":"Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions","created":"2024-03-25","cited_by_count":41,"area":"diffusion"},{"id":"2405.14858","title":"Mamba-R: Vision Mamba ALSO Needs Registers","created":"2024-05-23","cited_by_count":41,"area":"ssm"},{"id":"2506.08010","title":"Vision Transformers Don't Need Trained Registers","created":"2025-06-09","cited_by_count":41,"area":null},{"id":"2310.12973","title":"Frozen Transformers in Language Models Are Effective Visual Encoder Layers","created":"2023-10-19","cited_by_count":39,"area":null},{"id":"2411.09219","title":"Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation","created":"2024-11-14","cited_by_count":39,"area":null},{"id":"2410.14462","title":"LUDVIG: Learning-Free Uplifting of 2D Visual Features to Gaussian Splatting Scenes","created":"2024-10-18","cited_by_count":37,"area":null},{"id":"2410.16512","title":"TIPS: Text-Image Pretraining with Spatial awareness","created":"2024-10-21","cited_by_count":37,"area":null},{"id":"2603.15546","title":"Kimodo: Scaling Controllable Human Motion Generation","created":"2026-03-16","cited_by_count":37,"area":null},{"id":"2411.10086","title":"CorrCLIP: Reconstructing Patch Correlations in CLIP for Open-Vocabulary Semantic Segmentation","created":"2024-11-15","cited_by_count":34,"area":null},{"id":"2411.15869","title":"Self-Calibrated CLIP for Training-Free Open-Vocabulary Segmentation","created":"2024-11-24","cited_by_count":34,"area":"mllm"},{"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},{"id":"2505.04410","title":"DeCLIP: Decoupled Learning for Open-Vocabulary Dense Perception","created":"2025-05-07","cited_by_count":33,"area":null},{"id":"2506.21977","title":"StableCodec: Taming One-Step Diffusion for Extreme Image Compression","created":"2025-06-27","cited_by_count":33,"area":"diffusion"},{"id":"2406.07113","title":"Beyond Bare Queries: Open-Vocabulary Object Grounding with 3D Scene Graph","created":"2024-06-11","cited_by_count":32,"area":null},{"id":"2503.14405","title":"DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers","created":"2025-03-18","cited_by_count":32,"area":"distill"},{"id":"2506.23270","title":"Token Activation Map to Visually Explain Multimodal LLMs","created":"2025-06-29","cited_by_count":32,"area":"mllm"},{"id":"2506.17220","title":"Emergent Temporal Correspondences from Video Diffusion Transformers","created":"2025-06-20","cited_by_count":31,"area":"diffusion"},{"id":"2412.09072","title":"Cross-View Completion Models are Zero-shot Correspondence Estimators","created":"2024-12-12","cited_by_count":30,"area":null},{"id":"2502.11748","title":"ILIAS: Instance-Level Image retrieval At Scale","created":"2025-02-17","cited_by_count":30,"area":"mllm"},{"id":"2407.12427","title":"GeneralAD: Anomaly Detection Across Domains by Attending to Distorted Features","created":"2024-07-17","cited_by_count":29,"area":null},{"id":"2407.17465","title":"u-$\\mu$P: The Unit-Scaled Maximal Update Parametrization","created":"2024-07-24","cited_by_count":29,"area":null},{"id":"2411.15851","title":"ResCLIP: Residual Attention for Training-free Dense Vision-language Inference","created":"2024-11-24","cited_by_count":29,"area":"mllm"},{"id":"2602.11389","title":"Causal-JEPA: Learning World Models through Object-Level Latent Masking","created":"2026-02-11","cited_by_count":29,"area":"wm"},{"id":"2408.10945","title":"HiRED: Attention-Guided Token Dropping for Efficient Inference of High-Resolution Vision-Language Models","created":"2024-08-20","cited_by_count":28,"area":"mllm"}],"next_cursor":"100"}