Key papers

• VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding (2026)
  Xinhao Li et al.
  15.78
• DanceOPD: On-Policy Generative Field Distillation (2026)
  Wei Zhou et al.
  15.12
• Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models (2026)
  Lianghua Huang et al.
  14.10
• YOLOv12: Attention-Centric Real-Time Object Detectors (2025)
  Yunjie Tian and Qixiang Ye and David Doermann
  13.77
• UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning (2026)
  Niu Lian et al.
  13.33
• DomainShuttle: Freeform Open Domain Subject-driven Text-to-video Generation (2026)
  Nan Chen et al.
  13.30
• Qwen-Image-Agent: Bridging the Context Gap in Real-World Image Generation (2026)
  Zekai Zhang et al.
  13.23
• In-Context World Modeling for Robotic Control (2026)
  Siyin Wang et al.
  13.13
• Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation (2026)
  Hongyu Qu et al.
  12.88
• ViQ: Text-Aligned Visual Quantized Representations at Any Resolution (2026)
  Xumin Yu et al.
  12.83
• Orca: The World is in Your Mind (2026)
  Yihao Wang et al.
  12.82
• ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog (2026)
  Lingao Xiao et al.
  12.80
• Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence (2026)
  Shuailei Ma et al.
  12.80
• KeyFrame-Compass: Towards Comprehensive Evaluation of Keyframe-Conditioned Video Generation (2026)
  Yuqi Tang et al.
  12.77
• Translation as a Bridging Action: Transferring Manipulation Skills from Humans to Robots (2026)
  Sijin Chen et al.
  12.72
• ShutterMuse: Capture-Time Photography Guidance with MLLMs (2026)
  Jiayu Li et al.
  12.56
• LongE2V: Long-Horizon Event-based Video Reconstruction, Prediction, and Frame Interpolation with Video Diffusion Models (2026)
  Cheng-De Fan et al.
  12.46
• MultiRef-Compass: Towards Comprehensive Evaluation of Multi-Reference-to-Audio-Video Generation (2026)
  Xiaohan Zhang et al.
  12.46
• Multimodal Continuous Reasoning via Asymmetric Mutual Variational Learning (2026)
  Shijie Li et al.
  12.24
• Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning (2026)
  Hongxing Li et al.
  11.98
• VideoSearch-R1: Iterative Video Retrieval and Reasoning via Soft Query Refinement (2026)
  Seohyun Lee et al.
  11.82
• GEAR: Guided End-to-End AutoRegression for Image Synthesis (2026)
  Bin Lin et al.
  11.71
• OpenCoF: Learning to Reason Through Video Generation (2026)
  Xinyan Chen et al.
  11.71
• PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation (2026)
  Peiwen Zhang et al.
  11.68
• Enhancing In-context Panoramic Generation via Geometric-aware Pretraining (2026)
  Haoran Feng et al.
  11.45
• V-Zero: Answer-Label-Free On-Policy Distillation with Contrastive Evidence Gating for Fine-Grained Visual Reasoning (2026)
  Haoxiang Sun et al.
  11.42
• Fast LeWorldModel (2026)
  Yuntian Gao et al.
  11.25
• ABot-M0.5: Unified Mobility-and-Manipulation World Action Model (2026)
  Ronghan Chen et al.
  11.17
• MVTrack4Gen: Multi-View Point Tracking as Geometric Supervision for 4D Video Generation (2026)
  JoungBin Lee et al.
  11.09
• Qwen-Image-2.0-RL Technical Report (2026)
  Yixian Xu et al.
  11.03
• MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators (2026)
  Yushi Huang et al.
  11.01
• Infinite Worlds with Versatile Interactions (2026)
  Zelin Gao et al.
  10.96
• Domain Arithmetic: One-Shot VLA Adaptation under Environmental Shifts (2026)
  Taewook Kang et al.
  10.93
• LISA: Likelihood Score Alignment for Visual-condition Controllable Generation (2026)
  Yanghao Wang et al.
  10.63
• PhysiFormer: Learning to Simulate Mechanics in World Space (2026)
  Yiming Chen et al.
  10.39
• Video-MME-Logical: A Controlled Diagnostic Benchmark for Video Temporal-Logical Reasoning (2026)
  Hohin Kwan et al.
  10.28
• Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models (2026)
  Kaiwen Zheng et al.
  10.19
• Confidence-Aware Tool Orchestration for Robust Video Understanding (2026)
  Yangfan He et al.
  10.11
• WanSong v1.0 Technical Report (2026)
  Binghui Chen et al.
  10.06
• PixelEyes: Decoupling Perception and Reasoning for Pinpoint Visual Evidence Seeking (2026)
  Dengxian Gong et al.
  9.97
• OPSD-V: On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators (2026)
  Hongyu Liu et al.
  9.73
• VIABench: A Comprehensive Video Benchmark Collected from Blind Individuals for Visual Impairment Assistance (2026)
  Yunfeng Liu et al.
  9.73
• Video = World + Event Stream (2026)
  Lianghua Huang et al.
  9.72
• TESSERA v2: Scaling Pixel-wise Earth Foundation Models (2026)
  Zhengpeng Feng et al.
  9.63
• MG-RWKV: Multi-Grained Context-Aware RWKV for Temporal Forgery Localization (2026)
  Jingchen Ni et al.
  9.35
• Autonomous Scientific Discovery via Iterative Meta-Reflection (2026)
  Bingchen Zhao et al.
  9.35
• PhysEditWorld: A Large-Scale Dataset Toward Physics-Editable World Models (2026)
  Bin Hu et al.
  9.14
• Ink3D: Sculpting 3D Assets with Extremely Complex Textures via Video Generative Models (2026)
  Yue Han et al.
  8.87
• Focusing on What Matters: Saliency-Harnessing Accurate Routing for Diffusion MoE (2026)
  Haoyou Deng et al.
  8.82
• LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing (2026)
  Xinyu Wang et al.
  8.81
• TryOnCrafter: Unleashing Camera Trajectories for Realistic Video Virtual Try-on via a Renderable 4D Try-on Proxy (2026)
  Hao Sun et al.
  8.51
• NoPA: Non-Parametric Online 3D Scene Graph Generation (2026)
  Qi Xun Yeo et al.
  8.48
• Hierarchical Denoising For Multi-Step Visual Reasoning (2026)
  Zezhong Qian et al.
  8.47
• AVTok: 1D Unified Tokenization for Holistic Audio-Video Generation (2026)
  Kien T. Pham et al.
  8.42
• ProMSA:Progressive Multimodal Search Agents for Knowledge-Based Visual Question Answering (2026)
  ZhengXian Wu et al.
  8.40
• WildCity: A Real-World City-Scale Testbed for Rendering, Simulation, and Spatial Intelligence (2026)
  Xiangyu Han et al.
  8.24
• Are Text-to-Image Models Inductivist Turkeys? A Counterfactual Benchmark for Causal Reasoning (2026)
  Jiayi Lei et al.
  8.17
• Hallucination in World Models is Predictable and Preventable (2026)
  Nicklas Hansen et al.
  8.17
• ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation (2026)
  Kaifeng Zhao et al.
  7.69
• NormGuard: Reward-Preserving Norm Constraints in Flow-Matching Reinforcement Learning (2026)
  Tianlin Pan et al.
  7.31