9 papers
Parameter-Efficient Fine-Tuning for Spiking Point Cloud Models
Zihao Guo, Jihua Zhu, Yiding Sun +2
Spiking Neural Networks (SNNs) offer energy-efficient solutions for point cloud analysis on resource-constrained devices through event-driven computation. However, existing pre-tra…
SPARK: Susceptibility-Guided Profiling and Steering of Latent Reasoning States in Large Language Models
Dongxu Zhang, Yiding Sun, Zihao Guo +5
Reasoning failures in large language models (LLMs) are usually evaluated from final answers, but a wrong answer does not reveal why the model failed. The same incorrect output may…
GaussFusion: Towards Multimodal 3D Gaussian Pretraining
Zhixuan You, Jihua Zhu, Yiding Sun +5
3D Gaussian Splatting provides an explicit representation that jointly models geometry and appearance, serving as a scalable foundation for 3D representation learning. Existing pre…
Rich-Media Re-Ranker: A User Satisfaction-Driven LLM Re-ranking Framework for Rich-Media Search
Zihao Guo, Ligang Zhou, Zeyang Tang +5
Re-ranking plays a crucial role in modern information search systems by refining the ranking of initial search results to better satisfy user information needs. However, existing m…
Mantis: Mamba-native Tuning is Efficient for 3D Point Cloud Foundation Models
Zihao Guo, Jihua Zhu, Jian Liu +1
Pre-trained 3D point cloud foundation models (PFMs) have demonstrated strong transferability across diverse downstream tasks. However, full fine-tuning these models is computationa…
GraphKeeper: Graph Domain-Incremental Learning via Knowledge Disentanglement and Preservation
Zihao Guo, Qingyun Sun, Ziwei Zhang +4
Graph incremental learning (GIL), which continuously updates graph models by sequential knowledge acquisition, has garnered significant interest recently. However, existing GIL app…