Extending Structural Causal Models for Autonomous Vehicles to Simplify Temporal System Construction & Enable Dynamic…
MLIP: Efficient Multi-Perspective Language-Image Pretraining with Exhaustive Data Utilizationby Yu Zhang, Qi Zhang, Zixuan Gong,…
Decoupled Alignment for Robust Plug-and-Play Adaptationby Haozheng Luo, Jiahao Yu, Wenxin Zhang, Jialong Li, Jerry…
SuperGaussian: Repurposing Video Models for 3D Super Resolutionby Yuan Shen, Duygu Ceylan, Paul Guerrero, Zexiang…
Compositional 4D Dynamic Scenes Understanding with Physics Priors for Video Question Answeringby Xingrui Wang, Wufei…
The Embodied World Model Based on LLM with Visual Information and Prediction-Oriented Promptsby Wakana Haijima,…
Representing Animatable Avatar via Factorized Neural Fieldsby Chunjin Song, Zhijie Wu, Bastian Wandt, Leonid Sigal,…
Automatic Instruction Evolving for Large Language Modelsby Weihao Zeng, Can Xu, Yingxiu Zhao, Jian-Guang Lou,…
PruNeRF: Segment-Centric Dataset Pruning via 3D Spatial Consistencyby Yeonsung Jung, Heecheol Yun, Joonhyung Park, Jin-Hwa…
Diffusion Features to Bridge Domain Gap for Semantic Segmentationby Yuxiang Ji, Boyong He, Chenyuan Qu,…