joint optimization
- CLIPGaussian: Universal and Multimodal Style Transfer Based on Gaussian Splatting
- Co-Reinforcement Learning for Unified Multimodal Understanding and Generation
- CovMatch: Cross-Covariance Guided Multimodal Dataset Distillation with Trainable Text Encoder
- DiffE2E: Rethinking End-to-End Driving with a Hybrid Diffusion-Regression-Classification Policy
- End-to-End Vision Tokenizer Tuning
- Eve3D: Elevating Vision Models for Enhanced 3D Surface Reconstruction via Gaussian Splatting
- Exploring Neural Granger Causality with xLSTMs: Unveiling Temporal Dependencies in Complex Data
- FPSAttention: Training-Aware FP8 and Sparsity Co-Design for Fast Video Diffusion
- Learning Neural Exposure Fields for View Synthesis
- Pareto-Optimal Energy Alignment for Designing Nature-Like Antibodies
- UniMotion: A Unified Motion Framework for Simulation, Prediction and Planning