5 papers
Intrinsic Gradient Suppression for Label-Noise Prompt Tuning in Vision-Language Models
Jiayu Li, Jiaxin Qi, Sheng Zhou +2
Contrastive vision-language models like CLIP exhibit remarkable zero-shot generalization. However, prompt tuning remains highly sensitive to label noise, as mislabeled samples gene…
Self-Guided Process Reward Optimization with Redefined Step-wise Advantage for Process Reinforcement Learning
Wu Fei, Hao Kong, Shuxian Liang +5
Process Reinforcement Learning~(PRL) has demonstrated considerable potential in enhancing the reasoning capabilities of Large Language Models~(LLMs). However, introducing additiona…
Communication-Efficient and Personalized Federated Foundation Model Fine-Tuning via Tri-Matrix Adaptation
Yongle Li, Bo Liu, Sheng Huang +3
In federated learning, fine-tuning pre-trained foundation models poses significant challenges, particularly regarding high communication cost and suboptimal model performance due t…
Efficient Token Compression for Vision Transformer with Spatial Information Preserved
Junzhu Mao, Yang Shen, Jinyang Guo +2
Token compression is essential for reducing the computational and memory requirements of transformer models, enabling their deployment in resource-constrained environments. In this…
Semi-supervised Semantic Segmentation with Multi-Constraint Consistency Learning
Jianjian Yin, Tao Chen, Gensheng Pei +3
Consistency regularization has prevailed in semi-supervised semantic segmentation and achieved promising performance. However, existing methods typically concentrate on enhancing t…