199 citations · 209 across the 32 of their papers we have counts for
11 papers · 1 filter
Pushing the Limits of Distillation-Based Continual Learning via Classifier-Proximal Lightweight Plugins
Zhiming Xu, Baile Xu, Jian Zhao +2
Continual learning requires models to learn continuously while preserving prior knowledge under evolving data streams. Distillation-based methods are appealing for retaining past k…
On-the-Fly Data Augmentation via Gradient-Guided and Sample-Aware Influence Estimation
Suorong Yang, Jie Zong, Lihang Wang +6
Data augmentation has been widely employed to improve the generalization of deep neural networks. Most existing methods apply fixed or random transformations. However, we find that…
Exposing Hallucinations To Suppress Them: VLMs Representation Editing With Generative Anchors
Youxu Shi, Suorong Yang, Dong Liu
Multimodal large language models (MLLMs) have achieved remarkable success across diverse vision-language tasks, yet they remain highly susceptible to hallucinations, producing cont…
IPF-RDA: An Information-Preserving Framework for Robust Data Augmentation
Suorong Yang, Hongchao Yang, Suhan Guo +2
Data augmentation is widely utilized as an effective technique to enhance the generalization performance of deep models. However, data augmentation may inevitably introduce distrib…
-AttnMask: Attention-Guided Masked Hidden States for Efficient Data Selection and Augmentation
Jucheng Hu, Suorong Yang, Dongzhan Zhou
Visual Instruction Finetuning (VIF) is pivotal for post-training Vision-Language Models (VLMs). Unlike unimodal instruction finetuning in plain-text large language models, which ma…
Multimodal-Guided Dynamic Dataset Pruning for Robust and Efficient Data-Centric Learning
Suorong Yang, Peijia Li, Yujie Liu +5
Modern deep models are trained on large real-world datasets, where data quality varies and redundancy is common. Data-centric approaches such as dataset pruning have shown promise…
Neural-Driven Image Editing
Pengfei Zhou, Jie Xia, Xiaopeng Peng +15
Traditional image editing typically relies on manual prompting, making it labor-intensive and inaccessible to individuals with limited motor control or language abilities. Leveragi…
RL-Selector: Reinforcement Learning-Guided Data Selection via Redundancy Assessment
Suorong Yang, Peijia Li, Furao Shen +1
Modern deep architectures often rely on large-scale datasets, but training on these datasets incurs high computational and storage overhead. Real-world datasets often contain subst…
Position: Intelligent Science Laboratory Requires the Integration of Cognitive and Embodied AI
Sha Zhang, Suorong Yang, Tong Xie +18
Scientific discovery has long been constrained by human limitations in expertise, physical capability, and sleep cycles. The recent rise of AI scientists and automated laboratories…
A Smart Multimodal Healthcare Copilot with Powerful LLM Reasoning
Xuejiao Zhao, Siyan Liu, Su-Yin Yang +1
Misdiagnosis causes significant harm to healthcare systems worldwide, leading to increased costs and patient risks. MedRAG is a smart multimodal healthcare copilot equipped with po…
When Dynamic Data Selection Meets Data Augmentation
Suorong Yang, Peng Ye, Furao Shen +1
Dynamic data selection aims to accelerate training with lossless performance. However, reducing training data inherently limits data diversity, potentially hindering generalization…