activity
20242026
collaborators

9 papers

cs.CV2026

Just Noticeable Difference Modeling for Token Compression in Vision-Language-Action Models

Zhuoyuan Li, Rui Zhao, Jin Wang +5

Token compression has become a key technique for reducing the inference cost of large foundation models, with approaches such as token pruning and KV-cache reuse widely adopted in…

physics.optics2026

Plug-and-play endoscopic OCT enabled by a fully fiber-integrated 3D-printed probe

Yihan Wang, Ruilin You, Jiabin Chen +5

Endoscopic optical coherence tomography (OCT) brings depth-resolved imaging into small lumens and confined spaces, but each probe must be assembled from spliced, cleaved, and align…

cs.CV2026

Current Injection Spiking Neural Network for Infrared and Visible Image Fusion

Rui Zhao, Zhuoyuan Li, Wenrui Li +4

Infrared and visible image fusion (IVIF) integrates the complementary information of two modalities into a single image with richer scene content. While existing methods are largel…

cs.CV2026

RAVE: Rate-Adaptive Visual Encoding for 3D Gaussian Splatting

Hoang-Nhat Tran, Francesco Di Sario, Gabriele Spadaro +2

Recent advances in neural scene representations have transformed immersive multimedia, with 3D Gaussian Splatting (3DGS) enabling real-time photorealistic rendering. Despite its ef…

cs.CV2025

Generative Models at the Frontier of Compression: A Survey on Generative Face Video Coding

Bolin Chen, Shanzhi Yin, Goluck Konuko +4

The rise of deep generative models has greatly advanced video compression, reshaping the paradigm of face video coding through their powerful capability for semantic-aware represen…

cs.CV2025

Denoising Diffusion Probabilistic Model for Point Cloud Compression at Low Bit-Rates

Gabriele Spadaro, Alberto Presta, Jhony H. Giraldo +5

Efficient compression of low-bit-rate point clouds is critical for bandwidth-constrained applications. However, existing techniques mainly focus on high-fidelity reconstruction, re…