5 papers
Semi-Supervised Noise Adaptation: Transferring Knowledge from Noise Domain
Yuan Yao, Jin Song, Huixia Li +3
Transfer learning aims to facilitate the learning of a target domain by transferring knowledge from a source domain. The source domain typically contains semantically meaningful sa…
Search More, Think Less: Rethinking Long-Horizon Agentic Search for Efficiency and Generalization
Qianben Chen, Tianrui Qin, King Zhu +21
Recent deep research agents primarily improve performance by scaling reasoning depth, but this leads to high inference cost and latency in search-intensive scenarios. Moreover, gen…
Few Shot Semi-Supervised Learning for Abnormal Stop Detection from Sparse GPS Trajectories
Muhammad Ayub Sabir, Junbiao Pang, Jiaqi Wu +1
Abnormal stop detection (ASD) in intercity coach transportation is critical for ensuring passenger safety, operational reliability, and regulatory compliance. However, two key chal…
Uncertainty-aware Long-tailed Weights Model the Utility of Pseudo-labels for Semi-supervised Learning
Jiaqi Wu, Junbiao Pang, Qingming Huang
Current Semi-supervised Learning (SSL) adopts the pseudo-labeling strategy and further filters pseudo-labels based on confidence thresholds. However, this mechanism has notable dra…
In-Distribution Consistency Regularization Improves the Generalization of Quantization-Aware Training
Junbiao Pang, Tianyang Cai, Baochang Zhang +1
Although existing Quantization-Aware Training (QAT) methods intensively depend on knowledge distillation to guarantee performance, QAT still suffers from severe performance drop. T…