Kavli Affiliate: Zheng Zhu | First 5 Authors: Yuan Xu, Yuan Xu, , , | Summary: Imitation learning based policies perform well in robotic manipulation, but they often degrade under *egocentric viewpoint shifts* when trained from a single egocentric viewpoint. To address this issue, we present **EgoDemoGen**, a framework that generates *paired* novel egocentric demonstrations […]
Kavli Affiliate: Zheng Zhu | First 5 Authors: Zhehao Dong, Zhehao Dong, , , | Summary: Vision-language-action (VLA) models increasingly rely on diverse training data to achieve robust generalization. However, collecting large-scale real-world robot manipulation data across varied object appearances and environmental conditions remains prohibitively time-consuming and expensive. To overcome this bottleneck, we propose Embodied […]
Kavli Affiliate: Zheng Zhu | First 5 Authors: Haoyun Li, Haoyun Li, , , | Summary: Vision Language Action (VLA) models derive their generalization capability from diverse training data, yet collecting embodied robot interaction data remains prohibitively expensive. In contrast, human demonstration videos are far more scalable and cost-efficient to collect, and recent studies confirm […]
Kavli Affiliate: Long Zhang | First 5 Authors: Lingwen Deng, Lingwen Deng, , , | Summary: Parameter-Preserving Knowledge Editing (PPKE) enables updating models with new or corrected information without retraining or parameter adjustment. Recent PPKE approaches based on knowledge graphs (KG) to extend knowledge editing (KE) capabilities to multi-hop question answering (MHQA). However, these methods […]
Kavli Affiliate: Long Zhang | First 5 Authors: Yu Chen, Yu Chen, , , | Summary: Fine-tuning large pre-trained models for downstream tasks has become a fundamental approach in natural language processing. Fully fine-tuning all model parameters is computationally expensive and memory-intensive, especially in resource-constrained environments. Existing parameter-efficient fine-tuning methods reduce the number of trainable […]
Kavli Affiliate: Long Zhang | First 5 Authors: Jiaxun Yang, Jiaxun Yang, , , | Summary: Chinese Patronizing and Condescending Language (CPCL) is an implicitly discriminatory toxic speech targeting vulnerable groups on Chinese video platforms. The existing dataset lacks user comments, which are a direct reflection of video content. This undermines the model’s understanding of […]
Kavli Affiliate: Gang Su | First 5 Authors: Chun-Yi Xue, Chun-Yi Xue, , , | Summary: We demonstrate that spin PN junctions-magnetic semiconductor homojunctions with spin splitting-induced band offsets-fundamentally redefine carrier transport via spin-dependent recom bination probabilities. By integrating this mechanism into the Shockley model, we predict a near 100 enhancement in magnetoresistance sensitivity under […]
Kavli Affiliate: Cheng Peng | First 5 Authors: Deming Li, Deming Li, , , | Summary: In-the-wild photo collections often contain limited volumes of imagery and exhibit multiple appearances, e.g., taken at different times of day or seasons, posing significant challenges to scene reconstruction and novel view synthesis. Although recent adaptations of Neural Radiance Field […]
Kavli Affiliate: Cheng Peng | First 5 Authors: Deming Li, Deming Li, , , | Summary: In-the-wild photo collections often contain limited volumes of imagery and exhibit multiple appearances, e.g., taken at different times of day or seasons, posing significant challenges to scene reconstruction and novel view synthesis. Although recent adaptations of Neural Radiance Field […]
Kavli Affiliate: Cheng Peng | First 5 Authors: Yuan Ni, Yuan Ni, , , | Summary: Implicit neural representations (INRs) have emerged as a compact and parametric alternative to discrete array-based data representations, encoding information directly in neural network weights to enable resolution-independent representation and memory efficiency. However, existing INR approaches, when constrained to compact […]