4 papers
HiLo-Token: Input-Adaptive High-Low Frequency Token Compression for Efficient Image Editing
Haoran You, Yotam Nitzan, Lingzhi Zhang +7
Creative image editing tools, such as Photoshop's Remove or Generative Fill buttons, are central to everyday customer use and account for a major share of traffic in Photoshop and…
Inline Critic Steers Image Editing
Weitai Kang, Xiaohang Zhan, Yizhou Wang +4
Instruction-based image editing exhibits heterogeneous difficulty not only across cases but also across regions of an image, motivating refinement approaches that allocate correcti…
UniSER: A Foundation Model for Unified Soft Effects Removal
Jingdong Zhang, Lingzhi Zhang, Qing Liu +12
Digital images are often degraded by soft effects such as lens flare, haze, shadows, and reflections, which reduce aesthetics even though the underlying pixels remain partially vis…
Cautious Next Token Prediction
Yizhou Wang, Lingzhi Zhang, Yue Bai +7
Next token prediction paradigm has been prevailing for autoregressive models in the era of LLMs. The current default sampling choice for popular LLMs is temperature scaling togethe…