9 papers
HyperCLIP++: Fine-tuning CLIP forOpen-vocabulary Semantic Segmentation in Hyperbolic Space
Zelin Peng, Zhengqin Xu, Changsong Wen +4
CLIP, a foundational vision-language model, has emerged as a powerful tool for open-vocabulary semantic segmentation. While freezing CLIP's text encoder is known to preserve its ge…
Why Struggle with Continuous Latents? Interpretable Discrete Latent Reasoning via Rendered Compression
Shuochen Chang, Qingyang Liu, Shaobo Wang +8
Large language models achieve high reasoning performance via explicit chain-of-thought and reinforcement learning, but require long output sequences and extended inference time. La…
MMRad-22K: A Structured Multimodal Evidence Dataset for Chest X-ray Report Generation
Yichen Zhao, Zelin Peng, Fenghe Tang +3
Chest X-ray (CXR) reporting follows a region-based clinical workflow in which radiologists inspect anatomical regions and integrate localized findings into a final report. However,…
HyperET: Efficient Training in Hyperbolic Space for Multi-modal Large Language Models
Zelin Peng, Zhengqin Xu, Qingyang Liu +2
Multi-modal large language models (MLLMs) have emerged as a transformative approach for aligning visual and textual understanding. They typically require extremely high computation…
Unlocking 3D Affordance Segmentation with 2D Semantic Knowledge
Yu Huang, Zelin Peng, Changsong Wen +2
Affordance segmentation aims to decompose 3D objects into parts that serve distinct functional roles, enabling models to reason about object interactions rather than mere recogniti…
AnimateScene: Camera-controllable Animation in Any Scene
Qingyang Liu, Bingjie Gao, Weiheng Huang +10
Recent advances in 3D scene reconstruction and 4D human animation have broadened adoption, but integrating the two remains difficult. Key challenges include placing humans at plaus…
NEARL: Interacted Query Adaptation with Orthogonal Regularization for Medical Vision-Language Understanding
Zelin Peng, Yichen Zhao, Yu Huang +5
Computer-aided medical image analysis is crucial for disease diagnosis and treatment planning. While vision-language models (VLMs) such as CLIP exhibit strong generalization abilit…
MedSeg-R: Reasoning Segmentation in Medical Images with Multimodal Large Language Models
Yu Huang, Zelin Peng, Yichen Zhao +3
Medical image segmentation is crucial for clinical diagnosis, yet existing models are limited by their reliance on explicit human instructions and lack the active reasoning capabil…
Parameter-efficient Fine-tuning in Hyperspherical Space for Open-vocabulary Semantic Segmentation
Zelin Peng, Zhengqin Xu, Zhilin Zeng +2
Open-vocabulary semantic segmentation seeks to label each pixel in an image with arbitrary text descriptions. Vision-language foundation models, especially CLIP, have recently emer…