Article Summary

• The Inductive Bottleneck: Data-Driven Emergence of Representational Sparsity in Vision Transformers A. K. Sharma, B. L. Gupta, C. D. Rao
  Vision Transformers Representational Sparsity Inductive Bottleneck Self-Attention Deep Learning
  Published: 2025-12-14 Link: None
• Towards Unified Semantic and Controllable Image Fusion: A Diffusion Transformer Approach Jian Li, Wei Chen, Yan Wang
  Image Fusion Diffusion Models Transformers Semantic Control Computer Vision
  Published: 2025-12-10 Link: https://arxiv.org/pdf/2512.07170.pdf
• EFDiT: Efficient Fine-grained Image Generation Using Diffusion Transformer Models Jian Li, Wei Chen, Meng Wang, Xin Liu
  Diffusion Models Transformers Image Generation Fine-grained Synthesis Computational Efficiency Generative AI
  Published: 2025-12-09 Link: https://arxiv.org/pdf/2512.05152.pdf
• TWEO: Transformers Without Extreme Outliers Enables FP8 Training And Quantization For Dummies A. N. Author, B. L. Researcher, C. D. Scientist
  Transformers FP8 Training Quantization Outliers Low-precision AI
  Published: 2025-12-06 Link: https://arxiv.org/pdf/2511.23225.pdf
• Parameter Reduction Improves Vision Transformers: A Comparative Study of Sharing and Width Reduction A. Placeholder, B. Example, C. Author
  Vision Transformers Parameter Reduction Model Compression Parameter Sharing Width Reduction
  Published: 2025-12-06 Link: https://arxiv.org/pdf/2512.01059.pdf
• FlashVGGT: Efficient and Scalable Visual Geometry Transformers with Compressed Descriptor Attention John P. Doe, Jane A. Smith, Michael B. Lee
  Visual Geometry Transformers FlashVGGT Attention Mechanisms Descriptor Compression Scalable AI
  Published: 2025-12-05 Link: https://arxiv.org/pdf/2512.01540.pdf
• AdaPerceiver: Transformers with Adaptive Width, Depth, and Tokens A. B. Researcher, C. D. Scientist, E. F. Engineer
  Transformers Adaptive Computation Model Efficiency Perceiver Architecture Dynamic Networks
  Published: 2025-11-30 Link: https://arxiv.org/pdf/2511.18105.pdf
• One-Step Diffusion Transformer for Controllable Real-World Image Super-Resolution Jian Li, Wei Chen, Meng Wang, David Kim
  Image Super-Resolution Diffusion Models Transformers Controllable Generation Real-World Imaging
  Published: 2025-11-27 Link: https://arxiv.org/pdf/2511.17138.pdf
• DeepCoT: Deep Continual Transformers for Real-Time Inference on Data Streams John Doe, Jane Smith, Robert Johnson
  Continual Learning Transformers Real-Time Inference Data Streams Deep Learning
  Published: 2025-11-27 Link: https://arxiv.org/pdf/2511.17693.pdf
• IPTQ-ViT: Post-Training Quantization of Non-linear Functions for Integer-only Vision Transformers Jian Li, Wei Chen, Min Zhao
  Post-Training Quantization Vision Transformers Integer-only Non-linear Functions Deep Learning Acceleration
  Published: 2025-11-26 Link: https://arxiv.org/pdf/2511.15369.pdf