{"total":236,"rows":[{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863,"area":null},{"id":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044,"area":null},{"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":"2412.04431","title":"Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis","created":"2024-12-05","cited_by_count":304,"area":null},{"id":"2607.02770","title":"Gemma 4 Technical Report","created":"2026-07-02","cited_by_count":259,"area":"mllm"},{"id":"2411.19666","title":"Multimodal Whole Slide Foundation Model for Pathology","created":"2024-11-29","cited_by_count":162,"area":null},{"id":"2507.10496","title":"Cameras as Relative Positional Encoding","created":"2025-07-14","cited_by_count":105,"area":null},{"id":"2507.02863","title":"Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer Memory","created":"2025-07-03","cited_by_count":87,"area":null},{"id":"2412.10958","title":"SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer","created":"2024-12-14","cited_by_count":56,"area":null},{"id":"2405.14591","title":"Base of RoPE Bounds Context Length","created":"2024-05-23","cited_by_count":52,"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":"2406.05127","title":"Towards Semantic Equivalence of Tokenization in Multimodal LLM","created":"2024-06-07","cited_by_count":45,"area":"mllm"},{"id":"2503.12271","title":"Reflect-DiT: Inference-Time Scaling for Text-to-Image Diffusion Transformers via In-Context Reflection","created":"2025-03-15","cited_by_count":43,"area":"lr"},{"id":"2412.01819","title":"Switti: Designing Scale-Wise Transformers for Text-to-Image Synthesis","created":"2024-12-02","cited_by_count":33,"area":null},{"id":"2504.09975","title":"OctGPT: Octree-based Multiscale Autoregressive Models for 3D Shape Generation","created":"2025-04-14","cited_by_count":30,"area":"diffusion"},{"id":"2509.02359","title":"Why Do MLLMs Struggle with Spatial Understanding? A Systematic Analysis from Data to Architecture","created":"2025-09-02","cited_by_count":30,"area":"lr"},{"id":"2508.15772","title":"Visual Autoregressive Modeling for Instruction-Guided Image Editing","created":"2025-08-21","cited_by_count":22,"area":"diffusion"},{"id":"2501.06838","title":"Generalized and Efficient 2D Gaussian Splatting for Arbitrary-scale Super-Resolution","created":"2025-01-12","cited_by_count":21,"area":null},{"id":"2508.10684","title":"MDNS: Masked Diffusion Neural Sampler via Stochastic Optimal Control","created":"2025-08-14","cited_by_count":21,"area":"diffusion"},{"id":"2603.03283","title":"Utonia: Toward One Encoder for All Point Clouds","created":"2026-03-03","cited_by_count":21,"area":null},{"id":"2502.02562","title":"Learning the RoPEs: Better 2D and 3D Position Encodings with STRING","created":"2025-02-04","cited_by_count":19,"area":null},{"id":"2507.02608","title":"Lost in Latent Space: An Empirical Study of Latent Diffusion Models for Physics Emulation","created":"2025-07-03","cited_by_count":19,"area":"diffusion"},{"id":"2406.10322","title":"LieRE: Lie Rotational Positional Encodings","created":"2024-06-14","cited_by_count":18,"area":null},{"id":"2506.03737","title":"ComRoPE: Scalable and Robust Rotary Position Embedding Parameterized by Trainable Commuting Angle Matrices","created":"2025-06-04","cited_by_count":18,"area":null},{"id":"2509.21574","title":"X-Streamer: Unified Human World Modeling with Audiovisual Interaction","created":"2025-09-25","cited_by_count":18,"area":"wm"},{"id":"2510.03824","title":"Proximal Diffusion Neural Sampler","created":"2025-10-04","cited_by_count":16,"area":null},{"id":"2608.07408","title":"Addressable Memory for Video World Models","created":"2026-08-07","cited_by_count":15,"area":"wm"},{"id":"2505.13344","title":"RoPECraft: Training-Free Motion Transfer with Trajectory-Guided RoPE Optimization on Diffusion Transformers","created":"2025-05-19","cited_by_count":14,"area":"diffusion"},{"id":"2510.20766","title":"DyPE: Dynamic Position Extrapolation for Ultra High Resolution Diffusion","created":"2025-10-23","cited_by_count":14,"area":"diffusion"},{"id":"2601.15275","title":"RayRoPE: Projective Ray Positional Encoding for Multi-view Attention","created":"2026-01-21","cited_by_count":14,"area":null},{"id":"2606.17030","title":"Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation","created":"2026-06-15","cited_by_count":14,"area":"wm"},{"id":"2512.18814","title":"EchoMotion: Unified Human Video and Motion Generation via Dual-Modality Diffusion Transformer","created":"2025-12-21","cited_by_count":13,"area":"diffusion"},{"id":"2602.08068","title":"ReRoPE: Repurposing RoPE for Relative Camera Control","created":"2026-02-08","cited_by_count":13,"area":"diffusion"},{"id":"2409.07188","title":"FuXi-2.0: Advancing machine learning weather forecasting model for practical applications","created":"2024-09-11","cited_by_count":11,"area":null},{"id":"2511.19827","title":"ReDirector: Creating Any-Length Video Retakes with Rotary Camera Encoding","created":"2025-11-25","cited_by_count":11,"area":null},{"id":"2405.13985","title":"LookHere: Vision Transformers with Directed Attention Generalize and Extrapolate","created":"2024-05-22","cited_by_count":10,"area":null},{"id":"2505.21771","title":"MMTABREAL: Real-World Benchmark for Multimodal Table Understanding","created":"2025-05-27","cited_by_count":9,"area":null},{"id":"2605.15741","title":"HyperDiT: Hyper-Connected Transformers for High-Fidelity Pixel-Space Diffusion","created":"2026-05-15","cited_by_count":9,"area":"diffusion"},{"id":"2506.07405","title":"RiemannFormer: A Framework for Attention in Curved Spaces","created":"2025-06-09","cited_by_count":8,"area":null},{"id":"2507.21960","title":"PanoSplatt3R: Leveraging Perspective Pretraining for Generalized Unposed Wide-Baseline Panorama Reconstruction","created":"2025-07-29","cited_by_count":8,"area":null},{"id":"2509.13523","title":"AERIS: Argonne Earth Systems Model for Reliable and Skillful Predictions","created":"2025-09-16","cited_by_count":8,"area":"diffusion"},{"id":"2510.09734","title":"ARROW: An Adaptive Rollout and Routing Method for Global Weather Forecasting","created":"2025-10-10","cited_by_count":8,"area":null},{"id":"2512.16975","title":"InfoTok: Adaptive Discrete Video Tokenizer via Information-Theoretic Compression","created":"2025-12-18","cited_by_count":8,"area":null},{"id":"2603.27105","title":"UniDAC: Universal Metric Depth Estimation for Any Camera","created":"2026-03-28","cited_by_count":8,"area":null},{"id":"2602.03227","title":"Spiral RoPE: Rotate Your Rotary Positional Embeddings in the 2D Plane","created":"2026-02-03","cited_by_count":7,"area":null},{"id":"2506.09193","title":"LaDCast: A Latent Diffusion Model for Medium-Range Ensemble Weather Forecasting","created":"2025-06-10","cited_by_count":6,"area":"diffusion"},{"id":"2507.09025","title":"Lizard: An Efficient Linearization Framework for Large Language Models","created":"2025-07-11","cited_by_count":6,"area":null},{"id":"2509.25001","title":"LVT: Large-Scale Scene Reconstruction via Local View Transformers","created":"2025-09-29","cited_by_count":6,"area":null},{"id":"2511.18452","title":"NAF: Zero-Shot Feature Upsampling via Neighborhood Attention Filtering","created":"2025-11-23","cited_by_count":6,"area":null},{"id":"2604.18747","title":"URoPE: Universal Relative Position Embedding across Geometric Spaces","created":"2026-04-20","cited_by_count":6,"area":null},{"id":"2605.30215","title":"D\\'ej\\`a View: Looping Transformers for Multi-View 3D Reconstruction","created":"2026-05-28","cited_by_count":6,"area":null},{"id":"2409.02529","title":"Sample what you cant compress","created":"2024-09-04","cited_by_count":5,"area":null},{"id":"2503.06671","title":"Emulating Self-attention with Convolution for Efficient Image Super-Resolution","created":"2025-03-09","cited_by_count":5,"area":null},{"id":"2503.11129","title":"Direction-Aware Diagonal Autoregressive Image Generation","created":"2025-03-14","cited_by_count":5,"area":null},{"id":"2503.18931","title":"Enhancing Vision Foundation Models via Multimodal Continual Pre-Training","created":"2025-03-24","cited_by_count":5,"area":null},{"id":"2512.07805","title":"Group Representational Position Encoding","created":"2025-12-08","cited_by_count":5,"area":null},{"id":"2601.16272","title":"GR3EN: Generative Relighting for 3D Environments","created":"2026-01-22","cited_by_count":5,"area":"diffusion"},{"id":"2602.11534","title":"Krause Synchronization Transformers","created":"2026-02-12","cited_by_count":5,"area":null},{"id":"2604.16429","title":"(Sparse) Attention to the Details: Preserving Spectral Fidelity in ML-based Weather Forecasting Models","created":"2026-04-06","cited_by_count":5,"area":null},{"id":"2606.23503","title":"UniverSat: Resolution- and Modality-Agnostic Transformers for Earth Observation","created":"2026-06-22","cited_by_count":5,"area":null},{"id":"2606.27345","title":"SCoPE: Sightline-Coordinate Positional Encoding for Video Diffusion Transformers","created":"2026-06-25","cited_by_count":5,"area":"diffusion"},{"id":"2504.06308","title":"Rethinking RoPE: A Mathematical Blueprint for N-dimensional Positional Embedding","created":"2025-04-07","cited_by_count":4,"area":null},{"id":"2505.20444","title":"HoPE: Hybrid of Position Embedding for Long Context Vision-Language Models","created":"2025-05-26","cited_by_count":4,"area":"mllm"},{"id":"2505.20535","title":"Rotary Masked Autoencoders are Versatile Learners","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2510.22936","title":"PPE: Positional Preservation Embedding for Token Compression in Multimodal Large Language Models","created":"2025-10-27","cited_by_count":4,"area":"mllm"},{"id":"2512.11229","title":"REST: Diffusion-based Real-time End-to-end Streaming Talking Head Generation via ID-Context Caching and Asynchronous Streaming Distillation","created":"2025-12-12","cited_by_count":4,"area":"diffusion"},{"id":"2601.04792","title":"PyramidalWan: On Making Pretrained Video Model Pyramidal for Efficient Inference","created":"2026-01-08","cited_by_count":4,"area":null},{"id":"2602.02128","title":"Scalable Spatio-Temporal SE(3) Diffusion for Long-Horizon Protein Dynamics","created":"2026-02-02","cited_by_count":4,"area":"diffusion"},{"id":"2602.03510","title":"Semantic Routing: Exploring Multi-Layer LLM Feature Weighting for Diffusion Transformers","created":"2026-02-03","cited_by_count":4,"area":"diffusion"},{"id":"2602.08243","title":"Discrete Adjoint Schr\\\"odinger Bridge Sampler","created":"2026-02-09","cited_by_count":4,"area":null},{"id":"2602.20685","title":"RAYNOVA: Scale-Temporal Autoregressive World Modeling in Ray Space","created":"2026-02-24","cited_by_count":4,"area":"wm"},{"id":"2603.02193","title":"Symbol-Equivariant Recurrent Reasoning Models","created":"2026-03-02","cited_by_count":4,"area":"lr"},{"id":"2603.15302","title":"Generative Video Compression with One-Dimensional Latent Representation","created":"2026-03-16","cited_by_count":4,"area":null},{"id":"2604.19609","title":"Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding","created":"2026-04-21","cited_by_count":4,"area":null},{"id":"2605.11704","title":"ScaleMoGen: Autoregressive Next-Scale Prediction for Human Motion Generation","created":"2026-05-12","cited_by_count":4,"area":null},{"id":"2408.06305","title":"From SAM to SAM 2: Exploring Improvements in Meta's Segment Anything Model","created":"2024-08-12","cited_by_count":3,"area":null},{"id":"2411.19261","title":"Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention","created":"2024-11-28","cited_by_count":3,"area":"diffusion"},{"id":"2503.04344","title":"LEDiT: Your Length-Extrapolatable Diffusion Transformer without Positional Encoding","created":"2025-03-06","cited_by_count":3,"area":"diffusion"},{"id":"2505.09466","title":"A 2D Semantic-Aware Position Encoding for Vision Transformers","created":"2025-05-14","cited_by_count":3,"area":null},{"id":"2506.01596","title":"Understanding and Improving Laplacian Positional Encodings For Temporal GNNs","created":"2025-06-02","cited_by_count":3,"area":null},{"id":"2506.11168","title":"WaveFormer: A Lightweight Transformer Model for sEMG-based Gesture Recognition","created":"2025-06-12","cited_by_count":3,"area":null},{"id":"2508.01537","title":"FluidFormer: Transformer with Continuous Convolution for Particle-based Fluid Simulation","created":"2025-08-03","cited_by_count":3,"area":null},{"id":"2510.23106","title":"Sampling from Energy distributions with Target Concrete Score Identity","created":"2025-10-27","cited_by_count":3,"area":null},{"id":"2511.08368","title":"A Circular Argument : Does RoPE need to be Equivariant for Vision?","created":"2025-11-11","cited_by_count":3,"area":null},{"id":"2602.18478","title":"ZUNA: Flexible EEG Superresolution with Position-Aware Diffusion Autoencoders","created":"2026-02-09","cited_by_count":3,"area":"diffusion"},{"id":"2604.07904","title":"Kuramoto Oscillatory Phase Encoding: Neuro-inspired Synchronization for Improved Learning Efficiency","created":"2026-04-09","cited_by_count":3,"area":null},{"id":"2604.10391","title":"FishRoPE: Projective Rotary Position Embeddings for Omnidirectional Visual Perception","created":"2026-04-12","cited_by_count":3,"area":null},{"id":"2605.06916","title":"Tyche: One Step Flow for Efficient Probabilistic Weather Forecasting","created":"2026-05-07","cited_by_count":3,"area":null},{"id":"2605.07191","title":"Attention Transfer Is Not Universally Effective for Vision Transformers","created":"2026-05-08","cited_by_count":3,"area":null},{"id":"2605.09196","title":"RigidFormer: Learning Rigid Dynamics using Transformers","created":"2026-05-09","cited_by_count":3,"area":null},{"id":"2605.09989","title":"StereoPolicy: Improving Robotic Manipulation Policies via Stereo Perception","created":"2026-05-11","cited_by_count":3,"area":"offlinerl"},{"id":"2605.22668","title":"SEGA: Spectral-Energy Guided Attention for Resolution Extrapolation in Diffusion Transformers","created":"2026-05-21","cited_by_count":3,"area":"diffusion"},{"id":"2502.05928","title":"ClinKD: Cross-Modal Clinical Knowledge Distiller For Multi-Task Medical Images","created":"2025-02-09","cited_by_count":2,"area":null},{"id":"2503.00132","title":"CNSv2: Probabilistic Correspondence Encoded Neural Image Servo","created":"2025-02-28","cited_by_count":2,"area":null},{"id":"2505.03113","title":"Image Recognition with Online Lightweight Vision Transformer: A Survey","created":"2025-05-06","cited_by_count":2,"area":null},{"id":"2505.16993","title":"Native Segmentation Vision Transformers","created":"2025-05-22","cited_by_count":2,"area":null},{"id":"2505.20032","title":"ViTaPEs: Visuotactile Position Encodings for Cross-Modal Alignment in Multimodal Transformers","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2505.23004","title":"QLIP: A Dynamic Quadtree Vision Prior Enhances MLLM Performance Without Retraining","created":"2025-05-29","cited_by_count":2,"area":"mllm"},{"id":"2506.13277","title":"SeqPE: Transformer with Sequential Position Encoding","created":"2025-06-16","cited_by_count":2,"area":null},{"id":"2507.18161","title":"Recent Trends in Distant Conversational Speech Recognition: A Review of CHiME-7 and 8 DASR Challenges","created":"2025-07-24","cited_by_count":2,"area":null}],"next_cursor":"100"}