Emu3.5: Native Multimodal Models are World Learners
Paper • 2510.26583 • Published • 114
Haoge Deng
Bitterdhg
AI & ML interests
None yet
Organizations
authored 5
papers 5 months ago
EVEv2: Improved Baselines for Encoder-Free Vision-Language Models
Paper • 2502.06788 • Published • 13
OmniGen2: Exploration to Advanced Multimodal Generation
Paper • 2506.18871 • Published • 78
CI-VID: A Coherent Interleaved Text-Video Dataset
Paper • 2507.01938 • Published • 1
Uniform Discrete Diffusion with Metric Path for Video Generation
Paper • 2510.24717 • Published • 42
authored 3
papers over 1 year ago
GeoDream: Disentangling 2D and Geometric Priors for High-Fidelity and Consistent 3D Generation
Paper • 2311.17971 • Published
Autoregressive Video Generation without Vector Quantization
Paper • 2412.14169 • Published • 14
You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale
Paper • 2412.06699 • Published • 12