works on

From the 1 of 7 linked papers with an AI index.

activity
20242026
collaborators

7 papers

cs.CV2026

Consistent Evidence, Robust Recognition: Faithful Attribution Regularization under Geometric Transformations

Xianghao Jiao, Ruoyu Chen, Wei Wang +6

Attribution methods are widely used to characterize the evidence underlying model predictions, yet their potential to improve model behavior remains underexplored. Attribution inco…

cs.CV2026

The Second LoViF 2026 Challenge on Real-World All-in-One Image Restoration: Methods and Results

Xiang Chen, Hao Li, Jiangxin Dong +89

This paper presents a review of the second LoViF Challenge on Real-World All-in-One Image Restoration. The challenge aims to advance unified image restoration under diverse real-wo…

cs.CV2026

Where Not to Learn: Prior-Aligned Training with Subset-based Attribution Constraints

Ruoyu Chen, Shangquan Sun, Xiaoqing Guo +8

The paper introduces a training approach that encodes human‑provided region priors and uses a subset‑selection attribution method to penalize models when their decision evidence fa…

cs.CV2026

Timestep Rescheduling in Diffusion Inversion

Shangquan Sun, Ting Gong, Zhirui Liu +5

Diffusion inversion, which maps images back to the Gaussian latent space of a diffusion model, is a critical task for image reconstruction and editing. While DDIM enables fast dete…

cs.LG2026

Can Attribution Predict Risk? From Multi-View Attribution to Planning Risk Signals in End-to-End Autonomous Driving

Le Yang, Ruoyu Chen, Haijun Liu +3

End-to-end autonomous driving models generate future trajectories from multi-view inputs, improving system integration but introducing opaque decisions and hard-to-localize risks.…

cs.CV2025

Semi-Supervised State-Space Model with Dynamic Stacking Filter for Real-World Video Deraining

Shangquan Sun, Wenqi Ren, Juxiang Zhou +3

Significant progress has been made in video restoration under rainy conditions over the past decade, largely propelled by advancements in deep learning. Nevertheless, existing meth…