4 papers
DRDN: Decoupled Representation Dynamic Network for From-Scratch ViT Class-Incremental Learning
Bingchen Huang, Yifu Chen, Zhiling Wang +1
Dynamic expansion methods for class-incremental learning (CIL) protect task-specific knowledge by growing dedicated tokens or subnetworks, yet our analyses suggest that classificat…
Retrieved Images as Visual Thought: Training-Free Multimodal In-Context Learning for the Open-vs-Closed Gap
Bingchen Huang, Zhiling Wang, Yifu Chen +1
Recent work on Thinking with Images makes vision a dynamic part of reasoning, but does so through generation: the model invokes external tools, synthesizes code, or imagines new im…
TDR: Task-Decoupled Retrieval with Fine-Grained LLM Feedback for In-Context Learning
Yifu Chen, Bingchen Huang, Zhiling Wang +4
In-context learning (ICL) has become a classic approach for enabling LLMs to handle various tasks based on a few input-output examples. The effectiveness of ICL heavily relies on t…
Improving Text-guided Object Inpainting with Semantic Pre-inpainting
Yifu Chen, Jingwen Chen, Yingwei Pan +4
Recent years have witnessed the success of large text-to-image diffusion models and their remarkable potential to generate high-quality images. The further pursuit of enhancing the…