collaborators

5 papers

cs.CV2026

Dissecting Embodied Abilities in Multimodal Language Models through Skill-level Evaluation and Diagnosis

Yu Qi, Haibo Zhao, Ziyu Guo +17

Understanding the capability bottlenecks of embodied multimodal large language models (MLLMs) is crucial for improving embodied agents. However, existing embodied benchmarks mainly…

cond-mat.str-el2025

Magnetic electron-hole asymmetry in cuprates: a computational revisit

Jiong Mei, Shao-Hang Shi, Ping Xu +5

In this work, we revisit the electron-hole asymmetry of antiferromagnetism in cuprates by studying the three-band Emery model. Using parameters relevant to LaCuO, we benchm…

cs.CV2025

SimpleGVR: A Simple Baseline for Latent-Cascaded Video Super-Resolution

Liangbin Xie, Yu Li, Shian Du +7

Latent diffusion models have emerged as a leading paradigm for efficient video generation. However, as user expectations shift toward higher-resolution outputs, relying solely on l…

cond-mat.supr-con2025

Unveiling the landscape of Mottness and its proximity to superconductivity in 4Hb-TaS

Ping Wu, Zhuying Wang, Yunmei Zhang +15

Mott physics is at the root of a plethora of many-body quantum phenomena in quantum materials. Recently, the stacked or twisted structures of van der Waals (vdW) materials have eme…

cs.CV2025

TurboFill: Adapting Few-step Text-to-image Model for Fast Image Inpainting

Liangbin Xie, Daniil Pakhomov, Zhonghao Wang +8

This paper introduces TurboFill, a fast image inpainting model that enhances a few-step text-to-image diffusion model with an inpainting adapter for high-quality and efficient inpa…