Papers

• AIBench: Evaluating Visual-Logical Consistency in Academic Illustration Generation (2026)
  Zhaohe Liao et al.
  1.94
• Task-Focused Memorization for Multimodal Agents (2026)
  Tao Zou et al.
  1.94
• Does VLA Even Know the Basics? Measuring Commonsense and World Knowledge Retention in Vision-Language-Action Models (2026)
  Nikita Kachaev et al.
  1.94
• Uni-Edit: Intelligent Editing Is A General Task For Unified Model Tuning (2026)
  Dian Zheng et al.
  1.89
• Vision-DeepResearch Benchmark: Rethinking Visual and Textual Search for Multimodal Large Language Models (2026)
  Yu Zeng et al.
  1.72
• OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference (2025)
  Xiangyu Zhao et al.
  1.28
• SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories (2025)
  Muzhi Zhu et al.
  1.28
• BIMBA: Selective-Scan Compression for Long-Range Video Question Answering (2025)
  Md Mohaiminul Islam et al.
  1.28
• MMSearch-R1: Incentivizing LMMs to Search (2025)
  Jinming Wu et al.
  1.28
• Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor (2025)
  Vatsal Agarwal et al.
  1.28
• MovieCORE: COgnitive REasoning in Movies (2025)
  Gueter Josmy Faure et al.
  1.28
• When Big Models Train Small Ones: Label-Free Model Parity Alignment for Efficient Visual Question Answering using Small VLMs (2025)
  Abhirama Subramanyam Penamakuri et al.
  1.28
• MedVLSynther: Synthesizing High-Quality Visual Question Answering from Medical Documents with Generator-Verifier LMMs (2025)
  Xiaoke Huang et al.
  1.28
• ToolScope: An Agentic Framework for Vision-Guided and Long-Horizon Tool Use (2025)
  Mengjie Deng et al.
  1.28
• HunyuanOCR Technical Report (2025)
  Hunyuan Vision Team et al.
  1.28
• World in a Frame: Understanding Culture Mixing as a New Challenge for Vision-Language Models (2025)
  Eunsu Kim et al.
  1.28
• AdaptVision: Efficient Vision-Language Models via Adaptive Visual Acquisition (2025)
  Zichuan Lin et al.
  1.28
• JMMMU-Pro: Image-based Japanese Multi-discipline Multimodal Understanding Benchmark via Vibe Benchmark Construction (2025)
  Atsuyuki Miyai et al.
  1.28
• Guiding Vision-Language Model Selection for Visual Question-Answering Across Tasks, Domains, and Knowledge Types (2024)
  Neelabh Sinha et al.
  —