#1 · Paper · May 11, 2021
Diffusion Models Beat GANs on Image Synthesis
Prafulla Dhariwal, Alex Nichol · arXiv
Best Papers for Computer Vision
Track this topic after sign-in.
Query conditions: topic=computer-vision, and type=paper
Top Picks
#2 · Paper · Feb 28, 2026
VDC-Agent: When Video Detailed Captioners Evolve Themselves via Agentic Self-Reflection
Qiang Wang, Xinyuan Gao, SongLin Dong, Jizhou Han, Jiangyang Li, Yuhang He, Yihong Gong · arXiv
#3 · Paper · May 22, 2017
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
Joao Carreira, Andrew Zisserman · arXiv
#4 · Paper · Feb 26, 2015
Human-level control through deep reinforcement learning
Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A. Rusu, Joel Veness, Demis Hassabis · Nature
#5 · Paper · Nov 2, 2017
Neural Discrete Representation Learning
Aaron van den Oord, Oriol Vinyals, Koray Kavukcuoglu · arXiv
#6 · Paper · Feb 22, 2026
A homogeneous view of asymptotic giant branch carbon stars as seen by Gaia
Tatsunori Hashimoto, Percy Liang, Xinyi Wang · arXiv
#7 · Paper · Jan 22, 2026
Visual Web Navigation Agents: Beyond the DOM
John Smith, Alice Chen, Wei Lin · arXiv
#8 · Paper · Feb 13, 2026
MonarchRT: Efficient Attention for Real-Time Video Generation
Krish Agarwal, Zhuoming Chen, Cheng Luo, Beidi Chen · arXiv
#9 · Paper · Feb 13, 2026
DeepGen 1.0: A Lightweight Unified Multimodal Model for Image Generation and Editing
Ying Yang, Fang Kang, Mengqi Zhang, Zheng Lian · arXiv
#10 · Paper · Feb 9, 2026
Inference-Only Prompt Projection for Safe Text-to-Image Generation
Minhyuk Lee, Hyekyung Yoon, Myungjoo Kang · arXiv
#11 · Paper · Feb 8, 2026
Mirage2Matter: A Physically Grounded Gaussian World Model from Video
Zhengqing Gao, Ziwen Li, Xin Wang, Tongliang Liu · arXiv
FAQ
How is this best Computer Vision papers page ranked?
This page ranks Computer Vision papers by topic match, content-type filter, checkout momentum, and freshness. The ranking is recalculated as new items and engagement signals arrive, so the top results stay practical for current workflows instead of remaining static or purely chronological.
What does the time scope in this URL mean?
The time suffix in this URL defines the publish-date window used for ranking. Year paths include items in that year, and YYYYMM paths include one calendar month. This makes comparisons cleaner when you want a focused snapshot rather than an all-time aggregate.
Is this list paid placement?
No. This ranking is editorial and signal-driven, not sponsored placement. Attendemia evaluates public metadata, source context, and usage momentum to rank candidates. Payment does not buy position, so readers can interpret the list as a curation surface rather than advertising inventory.