Ming-Flash-Omni: A Sparse, Unified Architecture for Multimodal Perception and Generation
Paper • 2510.24821 • Published • 42
Xiaolong Wang
Xiaolong-Wang
AI & ML interests
None yet
Recent Activity
liked a model about 11 hours ago
inclusionAI/ARGenSeg-8B new activity 4 days ago
inclusionAI/ARGenSeg-8B:Update README.md upvoted a paper about 1 month ago
TC-AE: Unlocking Token Capacity for Deep Compression AutoencodersOrganizations
None yet
authored 6
papers 7 months ago
ARGenSeg: Image Segmentation with Autoregressive Image Generation Model
Paper • 2510.20803 • Published • 12
Fine-Grained Cross-View Geo-Localization Using a Correlation-Aware Homography Estimator
Paper • 2308.16906 • Published • 1
PointLLM: Empowering Large Language Models to Understand Point Clouds
Paper • 2308.16911 • Published • 2
Ming-UniVision: Joint Image Understanding and Generation with a Unified Continuous Tokenizer
Paper • 2510.06590 • Published • 78
HomoMatcher: Dense Feature Matching Results with Semi-Dense Efficiency by Homography Estimation
Paper • 2411.06700 • Published • 1