Machine Learning Papers

Last 7 Days (July 29 – August 04, 2026)

← Previous Week

🏆 Top Papers This Week

#1 TOP PAPER (Score: 87)
Long Qian, Jiaqi Wei, Bingke Zhu ... · Cardiff University +7 · arXiv (Preprint)
Modern vision language models (VLMs) turn high-resolution images into long sequences of visual tokens. Every token traverses the language decoder and persists in its prompt KV cache, inflating inference cost and motivating aggressive visual compression. Existing score-based metho...
#2 TOP PAPER (Score: 86)
Wenxiao Fan, Jingling Fu, Fang Li ... · JD.com · arXiv
Vision-language models (VLMs) are expected to revise their reasoning when visual evidence changes. Failures to do so are often attributed to insufficient visual attention or contextual inertia, leaving unclear what models reuse instead of recomputing from the current image. We sh...
#3 TOP PAPER (Score: 85)
Yue Ma, Jiangming Wang, Yucheng Wang ... · University of Macau +1 · ACM Transactions on Graphics (TOG) 2026
We present LiveLight, the first diffusion-based framework for real-time streaming video relighting with interactive 3D lighting control. Achieving this is non-trivial, as it requires overcoming three critical challenges: effectively injecting dynamic 3D lighting into a diffusion ...