Key papers

• Spatial Temporal Transformer Network For Skeleton-based Action Recognition (2020)
  Chiara Plizzari, Marco Cannici, Matteo Matteucci
  17.06
• TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM (2026)
  Hengyi Xie et al.
  15.39
• TARS: Timestep-Aware Data Scaling for 3D-Free Video Re-Shooting (2026)
  Jiwen Liu et al.
  14.57
• Generative World Renderer at the Speed of Play (2026)
  Guixu Lin et al.
  14.26
• X-Lens: Real-Time Metric Depth Estimation with Heterogeneous Cameras (2026)
  Heng Zhou et al.
  13.95
• ABot-N1: Toward a General Visual Language Navigation Foundation Model (2026)
  Ruiyan Gong et al.
  13.91
• 4D Human-Scene Reconstruction from Low-Overlap Captures (2026)
  Minhyuk Hwang et al.
  13.47
• HumanCLAW: Can Vision-Language Models Act Through a Body? (2026)
  Li Siyao et al.
  13.46
• VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System (2026)
  Haodong Li et al.
  13.30
• PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space (2026)
  Sensen Gao et al.
  13.02
• Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots (2026)
  Ling Xu et al.
  12.99
• Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text (2026)
  Xu Wang et al.
  12.66
• Vision as Unified Multimodal Generation (2026)
  Xiaoyang Han et al.
  12.31
• ACE-Data-0: Human-Centric Ambient Capture as Embodied Data Engine (2026)
  Yukang Cao et al.
  12.21
• MPIE-Bench: Benchmarking Anatomically Plausible Multi-Person Interaction Editing (2026)
  Jiajia Lin et al.
  12.15
• Video Generation Models are General-Purpose Vision Learners (2026)
  Letian Wang et al.
  12.14
• JanusMesh: Fast and Zero-Shot 3D Visual Illusion Generation via Cross-Space Denoising (2026)
  Siang-Ling Zhang et al.
  11.44
• The Principle Of Diversity: Training Stronger Vision Transformers Calls For Reducing All Levels Of Redundancy (2022)
  Tianlong Chen, Zhenyu Zhang, Yu Cheng, et al.
  11.19
• MetaView: Monocular Novel View Synthesis with Scale-Aware Implicit Geometry Priors (2026)
  Yufei Cai et al.
  11.16
• Vision Pretraining for Dense Spatial Perception (2026)
  Zelin Fu et al.
  11.15
• Person Recognition In Personal Photo Collections (2017)
  Seong Joon Oh, Rodrigo Benenson, Mario Fritz, et al.
  10.97
• Current World Models Lack a Persistent State Core (2026)
  Jinpeng Lu et al.
  10.57
• Look No Deeper: Recognizing Places From Opposing Viewpoints Under Varying Scene Appearance Using Single-view Depth Estimation (2019)
  Sourav Garg, Madhu Babu, Thanuja Dharmasiri, et al.
  10.48
• Do All Visual Tokens Matter Equally? Object-Evidence Preserving Token Merging for Vision-Language Retrieval (2026)
  Suhyeong Park et al.
  10.42
• 3D Human Pose Perception From Egocentric Stereo Videos (2023)
  Hiroyasu Akada, Jian Wang, Vladislav Golyanik, et al.
  10.35
• See2Think: Do Multimodal Models Really Use Intermediate Visual States? (2026)
  Siyu Yan et al.
  10.19
• FLAT: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene Generation (2026)
  Orest Kupyn et al.
  9.94
• PanoWorld: Real-World Panoramic Generation (2026)
  Haoyuan Li et al.
  9.90
• Hallo4D: Multi-Modal Hallucination Mitigation for Consistent Spatio-Temporal Generation (2026)
  Hongbo Wang et al.
  9.78
• Masked Visual Actions for Unified World Modeling (2026)
  Hadi Alzayer et al.
  9.68
• Recurrent Sinusoidal INRs for Efficient High-Fidelity Representation (2026)
  Hyunmin Cho et al.
  9.68
• CONFLUX: A Latent Diffusion Model for 3D Chest-CT Synthesis with RL Post-Training (2026)
  Max Van Puyvelde et al.
  9.63
• MRS-VPR: A Multi-resolution Sampling Based Global Visual Place Recognition Method (2019)
  Peng Yin, Rangaprasad Arun Srivatsan, Yin Chen, et al.
  9.59
• Monte Carlo Energy Aggregation for Mobile 3D Gaussian Splatting (2026)
  Xiaobiao Du et al.
  9.48
• Towards Spatial Supersensing in the Wild (2026)
  Tianjun Gu et al.
  9.48
• SCSegamba: Lightweight Structure-Aware Vision Mamba for Crack Segmentation in Structures (2025)
  Hui Liu et al.
  9.31
• ReToken: One Token to Improve Vision-Language Models for Visual Retrieval (2026)
  Yao Xiao et al.
  9.14
• Ridge Estimation-Based Vision and Laser Ranging Fusion Localization Method for UAVs (2025)
  Huayu Huang et al.
  8.97
• Deform360: A Massive Multi-view Visuotactile Dataset for Deformable World Models (2026)
  Hongyu Li et al.
  8.80
• From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image Models (2026)
  Zanyi Wang et al.
  8.60
• From Darkness to Detail: Frequency-Aware SSMs for Low-Light Vision (2024)
  Eashan Adhikarla et al.
  8.59
• Let RGB Be the Language of Vision (2026)
  Timing Yang et al.
  8.51
• SceneActBench: Can Agents Act on the 3D Scenes They See? (2026)
  Yifei Zhao et al.
  8.51
• VISTA: View-Consistent Self-Verified Training for GUI Grounding (2026)
  Xinyu Qiu et al.
  8.46
• UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler (2025)
  Luigi Piccinelli et al.
  8.22
• MV-Forcing: Long Multi-View Video Generation via 4D-Grounded Spatio-Temporal Self-Forcing (2026)
  Gal Fiebelman et al.
  8.17
• ClinFusion: A Vision-Centric Multimodal LLM System for Holistic Medical Understanding (2026)
  Hangjie Yuan et al.
  8.17
• ProCUA-SFT Technical Report (2026)
  Jaehun Jung et al.
  8.13
• MuSViT: A Foundation Vision Model for Sheet Music Representation (2026)
  Carlos Penarrubia et al.
  8.13
• Improved Object Pose Estimation Via Deep Pre-touch Sensing (2022)
  Patrick Lancaster, Boling Yang, Joshua R. Smith
  8.09
• SUFLECA: Scaling Up Feature Learning for CAD-to-image Alignment (2026)
  Saad Ejaz et al.
  7.92
• GNM Head: A Generative aNthropometric Model of the human head (2026)
  Stylianos Ploumpis et al.
  7.79
• Dite-HRNet: Dynamic Lightweight High-Resolution Network for Human Pose Estimation (2022)
  Qun Li et al.
  7.50
• SynCity 3000: Bootstrapping Scene-Scale 3D Diffusion (2026)
  Paul Engstler et al.
  7.31
• LATO.2: Factorized 3D Mesh Generation with Vertex and Topology Flow (2026)
  Hang Long et al.
  7.31
• MM-OR: A Large Multimodal Operating Room Dataset for Semantic Understanding of High-Intensity Surgical Environments (2025)
  Ege \"Ozsoy et al.
  7.29
• SpheRoPE: Zero-Shot Optimization-Free 360 Panorama Generation with Spherical RoPE (2026)
  Or Hirschorn et al.
  7.25
• AthletePose3D: A Benchmark Dataset for 3D Human Pose Estimation and Kinematic Validation in Athletic Movements (2025)
  Calvin Yeung et al.
  6.96
• Walking in the Implicit: Interactive World Exploration via Neural Scene Representation (2026)
  Zhiqi Li et al.
  6.85
• nnInteractive: Redefining 3D Promptable Segmentation (2025)
  Fabian Isensee et al.
  6.78