6 papers
RISE: Adaptive Imagination for World Action Models
Hongbo Lu, Liang Yao, Chenghao He +5
World Action Models (WAMs) improve planning by incorporating future world evolution into action generation, yet existing methods allocate a fixed imagination budget to every scene.…
The DAWN of World-Action Interactive Models
Hongbo Lu, Liang Yao, Chenghao He +6
A plausible scene evolution depends on the maneuver being considered, while a good maneuver depends on how the scene may evolve. Existing World Action Models (WAMs) largely miss th…
VisionNVS: Self-Supervised Inpainting for Novel View Synthesis under the Virtual-Shift Paradigm
Hongbo Lu, Liang Yao, Chenghao He +4
A fundamental bottleneck in Novel View Synthesis (NVS) for autonomous driving is the inherent supervision gap on novel trajectories: models are tasked with synthesizing unseen view…
Momentum Auxiliary Network for Supervised Local Learning
Junhao Su, Changpeng Cai, Feiyu Zhu +4
Deep neural networks conventionally employ end-to-end backpropagation for their training process, which lacks biological credibility and triggers a locking dilemma during network p…
HPFF: Hierarchical Locally Supervised Learning with Patch Feature Fusion
Junhao Su, Chenghao He, Feiyu Zhu +3
Traditional deep learning relies on end-to-end backpropagation for training, but it suffers from drawbacks such as high memory consumption and not aligning with biological neural n…
SPEAK: Speech-Driven Pose and Emotion-Adjustable Talking Head Generation
Changpeng Cai, Guinan Guo, Jiao Li +7
Most earlier researches on talking face generation have focused on the synchronization of lip motion and speech content. However, head pose and facial emotions are equally importan…