Papers

Filtered to computer vision · clear filter

Browse by term

continual learning 64reinforcement learning 34large language models 17benchmarking 12vision-language models 10generative models 8language models 8video generation 7multimodal models 6natural language processing 6robotics 6world models 6benchmarks 5diffusion models 5on-policy distillation 5policy optimization 5scalability 5self-distillation 5vision-language-action models 5autoregressive models 4computer vision 4diffusion transformers 4LLMs 4multimodal large language models 4verifiable rewards 4attention mechanisms 3embodied intelligence 3image editing 3long-term memory 3multimodal learning 3

Matching papers

MPIE-Bench: Benchmarking Anatomically Plausible Multi-Person Interaction Editing

37 upvotes · 30 JUL 2026 · Jiajia Lin, Mingxuan Du, Tuowen Zhou et al.

This paper introduces a benchmark to evaluate the performance of models in editing multi-person images, focusing on anatomical and geometric accuracy. Practitioners in the field of computer vision and image editing might care about this research as it aims to improve the quality of human-like images with multiple people.

computer visionimage editingmulti-person scenescontact densitymesh reconstructionanatomical accuracy

Oxygen-TryOn: Fashion-Native Foundation Model for Any-item Virtual Try-On

26 upvotes · 23 JUL 2026 · Yong Liu, Xiaolong Fu, Zihang Xu et al.

This paper introduces Oxygen-TryOn, a new AI model that can generate photorealistic images of people wearing any fashion item, in any setting. Practitioners in the fashion industry might care about this model because it can revolutionize virtual try-on, allowing for more realistic and diverse scenarios.

computer visionvirtual try-ongenerative modelsfashionimage synthesis

Trajectory-aware Cross-view Geo-localization with Sequential Observations

5 upvotes · 16 JUL 2026 · Tianyi Gao, Jiayu Lin, Danielle Beaulieu et al.

This paper develops a new method for cross-view geo-localization that uses video clips and route descriptions to improve accuracy, and introduces a unified framework that can handle both modalities. Practitioners in autonomous vehicle development or geospatial analysis might care about this research as it aims to address a common challenge in these fields.

computer visiongeo-localizationsequential observationsroute descriptionsvideo-text-satellite matching