LatentUMM: Dual Latent Alignment for Unified Multimodal Models
Paper • 2605.17766 • Published • 7
Li
Miser1234
AI & ML interests
None yet
Recent Activity
upvoted a paper 3 days ago
LatentUMM: Dual Latent Alignment for Unified Multimodal Models upvoted a paper 3 days ago
Geo-Align: Video Generation Alignment via Metric Geometry RewardOrganizations
None yet
upvoted 4
papers 3 days ago
Rethinking Muon Beyond Pretraining: Spectral Failures and High-Pass Remedies for VLA and RLVR
Paper • 2605.19282 • Published • 7
Geo-Align: Video Generation Alignment via Metric Geometry Reward
Paper • 2605.23903 • Published • 9
Rethinking Cross-Layer Information Routing in Diffusion Transformers
Paper • 2605.20708 • Published • 102