← Back to all news
arXiv AI By Jianwei Tang, Jian-Fang Hu, Tianming Liang, Xiaotong Lin, Jiangxin Sun, Wei-Shi Zheng, Jianhuang Lai

Human Motion Prediction via Continual Prior Compensation

Read the original on arXiv AI →

The paper introduces Continual Prior Compensation (CPC), a temporal continual learning framework that trains human motion prediction models in stages by dividing predictions for different future moments into subtasks. CPC mitigates forgetting of prior knowledge using a learnable Prior Compensation Factor (PCF) and is theoretically justified. An enhanced version, CPC++, adds Fine‑Grained PCF to estimate prior loss per subtask, and both frameworks are shown to be flexible, easily integrated with various backbones, and effective across three benchmark datasets.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
Jul 30

Gated Adaptation for Continual Learning in Human Activity Recognition

arXiv:2603. 10046v2 Announce Type: replace Abstract: Wearable sensors in Internet of Things (IoT) ecosystems increasingly support applications such as remote health monitoring, elderly care, and smart home automation, all of which rely on robust human activity recognition (HAR).

By Reza Rahimi Azghan, Gautham Krishna Gudur, Mohit Malu, Edison Thomaz, Giulia Pedrielli, Pavan Turaga, Hassan Ghasemzadeh
More like this →
arXiv AI
Sep 24

Parameter Importance-Driven Continual Learning for Foundation Models

The paper introduces PIECE, a Parameter Importance-Driven Continual Learning method that selectively updates only 0.1% of core parameters to preserve general abilities while learning new domain knowledge. PIECE employs two importance estimators—PIECE‑F using Fisher Information and PIECE‑S combining gradient and curvature information—to guide updates. Experiments on three language models and two multimodal models demonstrate that PIECE maintains general capabilities and achieves state‑of‑the‑art continual learning performance without accessing prior training data or adding parameter overhead.

By Lingxiang Wang, Hainan Zhang, Zhiming Zheng
llmsmultimodalbenchmarks
More like this →