Article Summary

• Autoregressive Image Generation Needs Only a Few Lines of Cached Tokens Author One, Author Two, Author Three
  autoregressive image generation image synthesis deep learning caching mechanism memory efficiency
  Published: 2025-12-09 Link: https://arxiv.org/pdf/2512.04857.pdf
• AlignVid: Training-Free Attention Scaling for Semantic Fidelity in Text-Guided Image-to-Video Generation John Doe, Jane Smith, Robert Johnson
  Text-to-video generation attention mechanisms semantic fidelity image generation deep learning
  Published: 2025-12-08 Link: https://arxiv.org/pdf/2512.01334.pdf
• Multi-GRPO: Multi-Group Advantage Estimation for Text-to-Image Generation with Tree-Based Trajectories and Multiple Rewards John Doe, Jane Smith, Alice Johnson
  text-to-image generation reinforcement learning tree-based trajectories multi-group advantage diffusion models
  Published: 2025-12-06 Link: https://arxiv.org/pdf/2512.00743.pdf
• Progress by Pieces: Test-Time Scaling for Autoregressive Image Generation Ava Chen, Ben Carter, Chloe Davis
  autoregressive models image generation test-time scaling computational efficiency deep learning
  Published: 2025-11-30 Link: https://arxiv.org/pdf/2511.21185.pdf
• Where Culture Fades: Revealing the Cultural Gap in Text-to-Image Generation A. B. Researcher, C. D. Developer, E. F. Innovator
  text-to-image generation cultural bias AI ethics generative models fairness in AI
  Published: 2025-11-30 Link: https://arxiv.org/pdf/2511.17282.pdf
• PairHuman: A High-Fidelity Photographic Dataset for Customized Dual-Person Generation Jianhui Sun, Yifan Zhao, Yuliang Deng, Tiankai Cheng
  dual-person generation photographic dataset human synthesis customization image generation
  Published: 2025-11-26 Link: https://arxiv.org/pdf/2511.16712.pdf
• Learning to Expand Images for Efficient Visual Autoregressive Modeling J. S. Kim, A. B. Lee, C. D. Miller
  autoregressive models image generation computational efficiency deep learning visual modeling
  Published: 2025-11-23 Link: https://arxiv.org/pdf/2511.15499.pdf
• MALeR: Improving Compositional Fidelity in Layout-Guided Generation Author Not Provided, Author Not Provided, Author Not Provided
  compositional fidelity layout-guided generation image generation AI placeholder
  Published: 2025-11-15 Link: https://arxiv.org/pdf/2511.06002.pdf