Apertus 1.5: From Open Text Models to Open Multimodal Reasoners Paper • 2610.15542 • Published 8 days ago • 45
LaDiR: Latent Diffusion Enhances LLMs for Text Reasoning Paper • 2510.04573 • Published Oct 6, 2025 • 2
Video Generation Models: A Survey of Post-Training and Alignment Paper • 2610.00812 • Published 19 days ago • 63
PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation Paper • 2609.38597 • Published 20 days ago • 34
UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement Paper • 2609.38721 • Published 19 days ago • 277
view article Article NVIDIA Kumo Tabular Sets a New Accuracy-Efficiency Frontier for Tabular Prediction nvidia • 20 days ago • 95
MLLMs Need 3D-Aware Representation Supervision for Scene Understanding Paper • 2506.01946 • Published Jun 2, 2025 • 3