activity
20242026
collaborators

11 papers

cs.CV2026

PixelIR: Fidelity-Perception Decoupling via Pixel-Space Image-Residual Flow Matching for Efficient One-Step Real-World Super-Resolution

Bingtian Qiao, Yue Shi, Yong Guo +2

Real-world image super-resolution (Real-ISR) aims to preserve structures supported by the degraded observation while reconstructing perceptually realistic details. However, existin…

cs.RO2026

H2R-Bench: Benchmarking Human-to-Robot Manipulation Video Generation in World Models

Dingyi Rong, Yue Shi, Chaofan Ma +6

Large-scale manipulation data is essential for robot learning, yet collecting robot demonstrations remains expensive and difficult to scale. Meanwhile, abundant egocentric human ma…

cs.RO2026

RoboProcessBench: Benchmarking Process-Aware Understanding in Vision-Language Robotic Manipulation

Dayu Xia, Yue Shi, Yao Mu +7

Vision-language models (VLMs) are increasingly explored as visual critics, reward generators, and failure detectors in robotic manipulation. These roles implicitly require models t…

cs.CV2026

Efficient One-Step Diffusion Restoration Model with Compact Token Compression and Linear Attention

Bingtian Qiao, Yue Shi, Yingjie Zhou +3

Real-world image super-resolution aims to recover high-quality images from complex and unknown real-world degradations. However, existing generative Real-ISR methods largely inheri…

cs.CV2026

EchoPrune: Interpreting Redundancy as Temporal Echoes for Efficient VideoLLMs

Jiameng Li, Minye Wu, Jiezhang Cao +2

Long-form video understanding remains challenging for Video Large Language Models (VideoLLMs), as the dense frame sampling introduces massive visual tokens while sparse sampling ri…

cs.CV2025

EvalTalker: Learning to Evaluate Real-Portrait-Driven Multi-Subject Talking Humans

Yingjie Zhou, Xilei Zhu, Siyu Ren +11

Speech-driven Talking Human (TH) generation, commonly known as "Talker," currently faces limitations in multi-subject driving capabilities. Extending this paradigm to "Multi-Talker…