activity
20242026
most citedFTS: A Framework to Find a Faithful TimeSieve

17 citations · 23 across the 41 of their papers we have counts for

collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2025

Text2Weight: Bridging Natural Language and Neural Network Weight Spaces

Bowen Tian, Wenshuo Chen, Zexi Li +3

How far are we really from automatically generating neural networks? While neural network weight generation shows promise, current approaches struggle with generalization to unseen…

cs.LG2025

Towards Reliable Time Series Forecasting under Future Uncertainty: Ambiguity and Novelty Rejection Mechanisms

Ninghui Feng, Songning Lai, Xin Zhou +9

In real-world time series forecasting, uncertainty and lack of reliable evaluation pose significant challenges. Notably, forecasting errors often arise from underfitting in-distrib…

cs.LG2024

Beyond Task Vectors: Selective Task Arithmetic Based on Importance Metrics

Tian Bowen, Lai Songning, Wu Jiemin +3

Pretrained models have revolutionized deep learning by enabling significant performance improvements across a wide range of tasks, leveraging large-scale, pre-learned knowledge rep…

cs.LG2024

Learning New Concepts, Remembering the Old: Continual Learning for Multimodal Concept Bottleneck Models

Songning Lai, Mingqian Liao, Zhangyi Hu +6

Concept Bottleneck Models (CBMs) enhance the interpretability of AI systems, particularly by bridging visual input with human-understandable concepts, effectively acting as a form…

cs.LG2024★ 1 cited

TS-ACL: Closed-Form Solution for Time Series-oriented Continual Learning

Jiaxu Li, Kejia Fan, Songning Lai +8

Time series classification underpins critical applications such as healthcare diagnostics and gesture-driven interactive systems in multimedia scenarios. However, time series class…

cs.LG2024★ 17 cited

FTS: A Framework to Find a Faithful TimeSieve

Songning Lai, Ninghui Feng, Haochen Sui +5

The field of time series forecasting has garnered significant attention in recent years, prompting the development of advanced models like TimeSieve, which demonstrates impressive…