collaborators

11 papers

cs.CR2026

Adversarial Prompts for Acceptance Collapse in Speculative Decoding

Run Wang, Chaoyi Zhou, Xi Liu +7

Lossless acceleration schemes, such as speculative decoding, promise significant inference speedups by relying on dynamic token-level alignment between a draft and a target model.…

cs.CV2026

Digital measurement of droplet flame diameter in microgravity combustion images using Segment Anything Model 2 with automatic prompt selection

Minghui Xu, Chaoyi Zhou, Aaron P. Cecil +3

Flame diameter is a key measurable parameter in microgravity droplet combustion, but its extraction from self-illuminated frames remains difficult because soot tails, blurred lumin…

cs.CV2026

HAD: Hallucination-Aware Diffusion Priors for 3D Reconstruction

Xi Liu, Weiwei Sun, Zhou Ren +3

Diffusion priors have recently demonstrated strong capability in enhancing the quality of sparse-view 3D reconstruction by augmenting training views at novel viewpoints, but they i…

cs.CV2026

Sat3R: Satellite DSM Reconstruction via RPC-Aware Depth Fine-tuning

Qiaoyi Yang, Chaoyi Zhou, Xi Liu +9

Accurate Digital Surface Model (DSM) reconstruction from satellite imagery is critical for applications such as disaster response, urban planning, and large-scale geographic mappin…

cs.CV2026

FF3R: Feedforward Feature 3D Reconstruction from Unconstrained views

Chaoyi Zhou, Run Wang, Feng Luo +4

Recent advances in vision foundation models have revolutionized geometry reconstruction and semantic understanding. Yet, most of the existing approaches treat these capabilities in…

cs.CV2026

Parameterized Brushstroke Style Transfer

Uma Meleti, Siyu Huang

Computer Vision-based Style Transfer techniques have been used for many years to represent artistic style. However, most contemporary methods have been restricted to the pixel doma…