Key papers

• 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
• PhiZero: A World Model Built Around Physical Language (2026)
  Shuyao Shang et al.
  15.29
• ABot-N1: Toward a General Visual Language Navigation Foundation Model (2026)
  Ruiyan Gong et al.
  13.91
• Scalable Visual Pretraining for Language Intelligence (2026)
  Yiming Zhang et al.
  13.85
• Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation (2026)
  Runhui Huang et al.
  13.52
• HumanCLAW: Can Vision-Language Models Act Through a Body? (2026)
  Siyao Li et al.
  13.46
• Visual Contrastive Self-Distillation (2026)
  Yijun Liang et al.
  13.32
• SynthDocBench: Controlled Benchmark for Long-Context Visual Document Understanding (2026)
  Abhigya Verma et al.
  13.06
• Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots (2026)
  Ling Xu et al.
  12.99
• OvisOCR2 Technical Report (2026)
  Shiyin Lu et al.
  12.87
• Beacon: Knowing When and How to Perform Agentic Visual Reasoning (2026)
  Qixun Wang et al.
  12.74
• 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
• LightMem-Ego: Your AI Memory for Everyday Life (2026)
  Yijun Chen et al.
  12.31
• VAD: Attributing Visual Evidence for Target Reconstruction in Multimodal On-Policy Distillation (2026)
  Kangning Zhang et al.
  11.50
• RefCaptioner: Multi-Reference Image-Grounded Video Captioning (2026)
  Tengfei Liu et al.
  11.42
• Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model (2026)
  Senqiao Yang et al.
  11.33
• DataEvolver: Self-Evolving Multi-Agent Data Construction for Text-Rich Image Generation (2026)
  Siyu Yan et al.
  10.92
• Do All Visual Tokens Matter Equally? Object-Evidence Preserving Token Merging for Vision-Language Retrieval (2026)
  Suhyeong Park et al.
  10.42
• See2Think: Do Multimodal Models Really Use Intermediate Visual States? (2026)
  Siyu Yan et al.
  10.19
• Scaling Native Multimodal Pre-Training From Scratch (2026)
  Haoyuan Wu et al.
  9.78
• MRS-VPR: A Multi-resolution Sampling Based Global Visual Place Recognition Method (2019)
  Peng Yin, Rangaprasad Arun Srivatsan, Yin Chen, et al.
  9.59
• IV-CoT: Implicit Visual Chain-of-Thought for Structure-Aware Text-to-Image Generation (2026)
  Zixuan Li et al.
  9.48
• Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning (2026)
  Junha Jung et al.
  9.43
• Parallelized Autoregressive Decoding for Omni-Modal Dense Video Captioning (2026)
  Wenzheng Zeng et al.
  9.28
• MonkeyOCRv2: A Visual-Text Foundation Model for Document AI (2026)
  Yuliang Liu et al.
  9.28
• ReToken: One Token to Improve Vision-Language Models for Visual Retrieval (2026)
  Yao Xiao et al.
  9.14
• RepWAM: World Action Modeling with Representation Visual-Action Tokenizers (2026)
  Junke Wang et al.
  9.08
• MODUS: Decoder-Only Any-to-Any Modeling of Diverse Modalities (2026)
  Mingqiao Ye et al.
  9.05
• MultAttnAttrib: Training-Free Multimodal Attribution in Long Document Question Answering (2026)
  Dang Quang Thien Tran et al.
  8.81
• Audio-Visual Flamingo: Open Audio-Visual Intelligence for Long and Complex Videos (2026)
  Sreyan Ghosh et al.
  8.80
• Visual prompt engineering for video models (2026)
  Robert Geirhos et al.
  8.79
• PerceptionBench: Evaluating Atomic Visual Perception in Multimodal Large Language Models (2026)
  Zichao Lin et al.
  8.60
• 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
• DecoupleMix: Decoupled Ratio Search and Convex Allocation for Scalable VLM Data Recipes (2026)
  Jiahao Xie et al.
  8.51
• VISTA: View-Consistent Self-Verified Training for GUI Grounding (2026)
  Xinyu Qiu et al.
  8.46
• Industryasseteqa: A Neurosymbolic Operational Intelligence System For Embodied Question Answering In Industrial Asset Maintenance (2026)
  Chathurangi Shyalika, Dhaval Patel, Amit Sheth
  8.20
• Attention Distillation: A Unified Approach to Visual Characteristics Transfer (2025)
  Yang Zhou et al.
  7.90
• TSCnet: A Text-driven Semantic-level Controllable Framework for Customized Low-Light Image Enhancement (2025)
  Miao Zhang et al.
  7.84
• Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detector (2025)
  Xiao Guo et al.
  7.84
• Hy-Embodied-VLM-1.0: Efficient Physical-World Agents (2026)
  Ziyi Wang et al.
  7.63
• Qwen3-VL Technical Report (2025)
  Shuai Bai et al.
  7.58
• Advancing WordArt-Oriented Scene Text Recognition: Datasets and Methods (2026)
  Xingsong Ye et al.
  7.58
• Unlocking the Visual Record of Materials Science: A Large-Scale Multimodal Dataset from Scientific Literature (2026)
  Subham Ghosh et al.
  7.58
• Low-rank HOCA: Efficient High-order Cross-modal Attention For Video Captioning (2019)
  Tao Jin, Siyu Huang, Yingming Li, et al.
  7.50
• HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better (2026)
  Gengluo Li et al.
  7.31
• Evidence Attribution in Visual Document Understanding without Coordinates or Region Labels (2026)
  Zhuchenyang Liu 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
• StylisticBias: A Few Human Visual Cues Drive Most Social Biases in MLLMs (2026)
  Shaghayegh Kolli et al.
  7.26
• GUICrafter: Weakly-Supervised GUI Agent Leveraging Massive Unannotated Screenshots (2026)
  Sunqi Fan et al.
  7.04
• RSRefSeg: Referring Remote Sensing Image Segmentation with Foundation Models (2025)
  Keyan Chen et al.
  6.85
• UltraViT: Latency-Optimized On-device Vision Encoder for Large Vision-Language Models (2026)
  Ioannis Maniadis Metaxas et al.
  6.69
• AFFORDANCE20Q: Evaluating Affordance Reasoning from Physical Properties (2026)
  Yifan Jiang et al.
  6.64
• InstanceControl: Controllable Complex Image Generation without Instance Labeling (2026)
  Xiaoyu Liu et al.
  6.64
• One Forward Beats Two: InnerZoom for Accurate and Efficient GUI Grounding (2026)
  Chen Liu et al.
  6.37
• Vilt: Vision-and-language Transformer Without Convolution Or Region Supervision (2021)
  Wonjae Kim, Bokyung Son, Ildoo Kim
  6.37
• PanoGen++: Domain-Adapted Text-Guided Panoramic Environment Generation for Vision-and-Language Navigation (2025)
  Sen Wang et al.
  6.36
• Image Captioning Evaluation in the Age of Multimodal LLMs: Challenges and Future Perspectives (2025)
  Sara Sarto et al.
  6.36
• Modeling Thousands of Human Annotators for Generalizable Text-to-Image Person Re-identification (2025)
  Jiayu Jiang et al.
  6.12