Dynamic Chunking for End-to-End Hierarchical Sequence Modeling Paper • 2507.07955 • Published 23 days ago • 21
Ming-Omni: A Unified Multimodal Model for Perception and Generation Paper • 2506.09344 • Published Jun 11 • 27
TransMamba: Flexibly Switching between Transformer and Mamba Paper • 2503.24067 • Published Mar 31 • 21
Chirpy3D: Continuous Part Latents for Creative 3D Bird Generation Paper • 2501.04144 • Published Jan 7 • 19
GoldFinch: High Performance RWKV/Transformer Hybrid with Linear Pre-Fill and Extreme KV-Cache Compression Paper • 2407.12077 • Published Jul 16, 2024 • 57
Scalable High-Resolution Pixel-Space Image Synthesis with Hourglass Diffusion Transformers Paper • 2401.11605 • Published Jan 21, 2024 • 23