collaborators

11 papers

physics.chem-ph2026

DPA4: Pushing the Accuracy-Cost Frontier of Interatomic Potentials with EMFA SO(2) Convolution

Tiancheng Li, Wentao Li, Anyang Peng +4

Machine-learning interatomic potentials now approach quantum-mechanical accuracy, but the most expressive equivariant architectures are costly to evaluate, and the leading ones dep…

cs.CV2026

STaR-KV: Spatio-Temporal Adaptive Re-weighting for KV Cache Compression in GUI Vision-Language Models

Yuhang Han, Wenzheng Yang, Yujie Chen +4

Vision-language-model-based graphical user interface (GUI) agents have shown broad automation capabilities, yet deployment is bottlenecked by a key-value (KV) cache that grows line…

cs.CV2026

ExtraVAR: Stage-Aware RoPE Remapping for Resolution Extrapolation in Visual Autoregressive Models

Feihong Yan, Shaoyu Liu, Haixuan Wang +4

Visual Autoregressive (VAR) models have emerged as a strong alternative to diffusion for image synthesis, yet their fixed training resolution prevents direct generation at higher r…

cs.CV2026

SpecEdit: Training-Free Acceleration for Diffusion based Image Editing via Semantic Locking

Zhengan Yan, Shikang Zheng, Haoran Qin +9

Diffusion-based image editing offers strong semantic controllability, but remains computationally expensive due to iterative high-resolution denoising over all spatial tokens. Dyna…

cs.CV2026

Beyond Fixed Formulas: Data-Driven Linear Predictor for Efficient Diffusion Models

Zhirong Shen, Rui Huang, Jiacheng Liu +6

To address the high sampling cost of Diffusion Transformers (DiTs), feature caching offers a training-free acceleration method. However, existing methods rely on hand-crafted forec…

cs.CV2026

Accelerating Diffusion-based Video Editing via Heterogeneous Caching: Beyond Full Computing at Sampled Denoising Timestep

Tianyi Liu, Ye Lu, Linfeng Zhang +5

Diffusion-based video editing has emerged as an important paradigm for high-quality and flexible content generation. However, despite their generality and strong modeling capacity,…