9 papers · 1 filter
Yo'City: Personalized and Boundless 3D Realistic City Scene Generation via Self-Critic Expansion
Keyang Lu, Sifan Zhou, Hongbin Xu +6
Realistic 3D city generation is fundamental to a wide range of applications, including virtual reality and digital twins. However, most existing methods rely on training a single d…
Spatial 3D-LLM: Exploring Spatial Awareness in 3D Vision-Language Models
Xiaoyan Wang, Zeju Li, Yifan Xu +5
New era has unlocked exciting possibilities for extending Large Language Models (LLMs) to tackle 3D vision-language tasks. However, most existing 3D multimodal LLMs (MLLMs) rely on…
UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter-Efficient Fine-Tuning of Large Models
Xueyan Zhang, Jinman Zhao, Zhifei Yang +4
This paper introduces Uniform Orthogonal Reinitialization Adaptation (UORA), a novel parameter-efficient fine-tuning (PEFT) approach for Large Language Models (LLMs). UORA achieves…
SepPrune: Structured Pruning for Efficient Deep Speech Separation
Yuqi Li, Kai Li, Xin Yin +6
Although deep learning has substantially advanced speech separation in recent years, most existing studies continue to prioritize separation quality while overlooking computational…
VidText: Towards Comprehensive Evaluation for Video Text Understanding
Zhoufaran Yang, Yan Shu, Jing Wang +8
Visual texts embedded in videos carry rich semantic information, which is crucial for both holistic video understanding and fine-grained reasoning about local human actions. Howeve…
MaRI: Material Retrieval Integration across Domains
Jianhui Wang, Zhifei Yang, Yangfan He +3
Accurate material retrieval is critical for creating realistic 3D assets. Existing methods rely on datasets that capture shape-invariant and lighting-varied representations of mate…
Gradient as Conditions: Rethinking HOG for All-in-one Image Restoration
Jiawei Wu, Zhifei Yang, Zhe Wang +1
All-in-one image restoration (AIR) aims to address diverse degradations within a unified model by leveraging informative degradation conditions to guide the restoration process. Ho…
MMGDreamer: Mixed-Modality Graph for Geometry-Controllable 3D Indoor Scene Generation
Zhifei Yang, Keyang Lu, Chao Zhang +9
Controllable 3D scene generation has extensive applications in virtual reality and interior design, where the generated scenes should exhibit high levels of realism and controllabi…
DiffPO: Diffusion-styled Preference Optimization for Efficient Inference-Time Alignment of Large Language Models
Ruizhe Chen, Wenhao Chai, Zhifei Yang +5
Inference-time alignment provides an efficient alternative for aligning LLMs with humans. However, these approaches still face challenges, such as limited scalability due to policy…