8 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…
Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning
Leichao Dong, Dongxu Zhang, Yiding Sun +4
Large reasoning models often solve problems through long chain-of-thought (CoT) traces, yet much of this computation is spent on redundant derivations, repeated self-verification,…
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…
Tri-Efficient Transfer Learning for Point Cloud Videos
Yiding Sun, Dongxu Zhang, Jihua Zhu +6
While point cloud foundation models have significantly advanced point cloud video understanding, existing parameter-efficient fine-tuning (PEFT) methods still suffer from two criti…
Beyond Next-Token Alignment: Distilling Multimodal Large Language Models via Token Interactions
Lin Chen, Xiaoke Zhao, Kun Ding +9
Multimodal Large Language Models (MLLMs) demonstrate impressive cross-modal capabilities, yet their substantial size poses significant deployment challenges. Knowledge distillation…
Align then Adapt: Rethinking Parameter-Efficient Transfer Learning in 4D Perception
Yiding Sun, Jihua Zhu, Haozhe Cheng +4
Point cloud video understanding is critical for robotics as it accurately encodes motion and scene interaction. We recognize that 4D datasets are far scarcer than 3D ones, which ha…
DSFC-Net: A Dual-Encoder Spatial and Frequency Co-Awareness Network for Rural Road Extraction
Zhengbo Zhang, Yihe Tian, Wanke Xia +6
Accurate extraction of rural roads from high-resolution remote sensing imagery is essential for infrastructure planning and sustainable development. However, this task presents uni…