7 papers
Self-Supervised Visual Prompting for Cross-Domain Road Damage Detection
Xi Xiao, Zhuxuanzi Wang, Mingqiao Mo +6
The deployment of automated pavement defect detection is often hindered by poor cross-domain generalization. Supervised detectors achieve strong in-domain accuracy but require cost…
Learning Straight Flows: Variational Flow Matching for Efficient Generation
Chenrui Ma, Xi Xiao, Tianyang Wang +2
Flow Matching has limited ability in achieving one-step generation due to its reliance on learned curved trajectories. Previous studies have attempted to address this limitation by…
CTR-LoRA: Curvature-Aware and Trust-Region Guided Low-Rank Adaptation for Large Language Models
Zhuxuanzi Wang, Mingqiao Mo, Xi Xiao +6
Parameter-efficient fine-tuning (PEFT) has become the standard approach for adapting large language models under limited compute and memory budgets. Although previous methods impro…
Stochastic Interpolants via Conditional Dependent Coupling
Chenrui Ma, Xi Xiao, Tianyang Wang +2
Existing image generation models face critical challenges regarding the trade-off between computation and fidelity. Specifically, models relying on a pretrained Variational Autoenc…
Can AI Dream of Unseen Galaxies? Conditional Diffusion Model for Galaxy Morphology Augmentation
Chenrui Ma, Zechang Sun, Tao Jing +4
Observational astronomy relies on visual feature identification to detect critical astrophysical phenomena. While machine learning (ML) increasingly automates this process, models…
Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions
Chenrui Ma, Xi Xiao, Tianyang Wang +1
Current text-driven image editing methods typically follow one of two directions: relying on large-scale, high-quality editing pair datasets to improve editing precision and divers…