11 papers
RoboAlign-R1: Distilled Multimodal Reward Alignment for Robot Video World Models
Hao Wu, Yuqi Li, Yuan Gao +10
Existing robot video world models are typically trained with low-level objectives such as reconstruction and perceptual similarity, which are poorly aligned with the capabilities t…
GaitKD: A Universal Decoupled Distillation Framework for Efficient Gait Recognition
Yuqi Li, Qian Zhou, Huiran Duan +5
Gait recognition is an attractive biometric modality for long-range and contact-free identification, but high-performing gait models often rely on deep and computationally expensiv…
The Fourth Challenge on Image Super-Resolution (4) at NTIRE 2026: Benchmark Results and Method Overview
Zheng Chen, Kai Liu, Jingkai Wang +150
This paper presents the NTIRE 2026 image super-resolution (4) challenge, one of the associated competitions of the NTIRE 2026 Workshop at CVPR 2026. The challenge aims to r…
Distilling Time Series Foundation Models for Efficient Forecasting
Yuqi Li, Kuiye Ding, Chuanguang Yang +2
Time Series foundation models (TSFMs) deliver strong forecasting performance through large-scale pretraining, but their large parameter sizes make deployment costly. While knowledg…
MMT-ARD: Multimodal Multi-Teacher Adversarial Distillation for Robust Vision-Language Models
Yuqi Li, Junhao Dong, Chuanguang Yang +5
Vision-Language Models (VLMs) are increasingly deployed in safety-critical applications, making their adversarial robustness a crucial concern. While adversarial knowledge distilla…
DDTime: Dataset Distillation with Spectral Alignment and Information Bottleneck for Time-Series Forecasting
Yuqi Li, Kuiye Ding, Chuanguang Yang +5
Time-series forecasting is fundamental across many domains, yet training accurate models often requires large-scale datasets and substantial computational resources. Dataset distil…