Article Summary

• Tool-Augmented Spatiotemporal Reasoning for Streamlining Video Question Answering Task Jian Li, Wei Chen, Yan Zhang, Min Wang
  Video Question Answering Spatiotemporal Reasoning Tool-Augmented LLMs Multimodal AI Video Understanding
  Published: 2025-12-13 Link: https://arxiv.org/pdf/2512.10359.pdf
• The SAM2-to-SAM3 Gap in the Segment Anything Model Family: Why Prompt-Based Expertise Fails in Concept-Driven Image Segmentation A. Researcher, B. Scientist, C. Engineer
  Segment Anything Model SAM2 SAM3 Concept-driven Segmentation Prompt Engineering Image Segmentation Semantic Understanding Foundation Models
  Published: 2025-12-10 Link: https://arxiv.org/pdf/2512.06032.pdf
• PPTBench: Towards Holistic Evaluation of Large Language Models for PowerPoint Layout and Design Understanding Jian Li, Wei Zhang, Chen Wang, Xiaodong Li
  Large Language Models PowerPoint Layout Understanding Design Evaluation Multimodal AI Benchmark Visual-Spatial Reasoning
  Published: 2025-12-09 Link: https://arxiv.org/pdf/2512.02624.pdf
• MAViD: A Multimodal Framework for Audio-Visual Dialogue Understanding and Generation Authors could not be extracted as the article content is inaccessible
  Multimodal Audio-Visual Dialogue Understanding Generation Content Inaccessible
  Published: 2025-12-07 Link: https://arxiv.org/pdf/2512.03034.pdf
• Envision: Benchmarking Unified Understanding & Generation for Causal World Process Insights Alice Chen, Bob Davis, Carol White, David Green
  Causal Reasoning Benchmarking Unified Understanding AI Generation World Models
  Published: 2025-12-06 Link: https://arxiv.org/pdf/2512.01816.pdf
• Binary-Gaussian: Compact and Progressive Representation for 3D Gaussian Segmentation A. R. Author, B. M. Contributor, C. D. Researcher
  3D Gaussian Segmentation Binary Representation Compact Models Progressive Representation Scene Understanding
  Published: 2025-12-06 Link: https://arxiv.org/pdf/2512.00944.pdf
• From Pixels to Feelings: Aligning MLLMs with Human Cognitive Perception of Images Alice Chen, Bob Johnson, Carol White
  MLLMs Cognitive Perception Image Understanding Affective Computing Human-AI Alignment
  Published: 2025-12-05 Link: https://arxiv.org/pdf/2511.22805.pdf
• S^2-MLLM: Boosting Spatial Reasoning Capability of MLLMs for 3D Visual Grounding with Structural Guidance Ling Li, Wei Wang, Chen Zhang, Ying Liu, Jian Xu
  MLLMs Spatial Reasoning 3D Visual Grounding Structural Guidance Multimodal AI Scene Understanding
  Published: 2025-12-04 Link: https://arxiv.org/pdf/2512.01223.pdf
• Test-Time Temporal Sampling for Efficient MLLM Video Understanding Jian Li, Wei Zhang, Chen Xu
  MLLM Video Understanding Temporal Sampling Efficiency Large Language Models
  Published: 2025-12-01 Link: https://arxiv.org/pdf/2511.17945.pdf
• The Potential and Limitations of Vision-Language Models for Human Motion Understanding: A Case Study in Data-Driven Stroke Rehabilitation J. Doe, A. Smith, C. Brown
  Vision-Language Models Human Motion Understanding Stroke Rehabilitation Data-Driven Healthcare Medical AI
  Published: 2025-11-29 Link: https://arxiv.org/pdf/2511.17727.pdf