activity
20242026
collaborators

10 papers

cs.LG2026

Before Fusion, Ask What to Keep: Contextual Calibration of Multimodal Signals

Jiyuan Liu, Liangwei Nathan Zheng, Wei Emma Zhang +2

Multimodal systems often benefit from combining information across language, sound, and visual streams, but this benefit is not guaranteed. A modality that is useful for one input…

cs.LG2026

Tackling Multimodal Learning Challenges with Mixture-of-Expert: A Survey

Liangwei Nathan Zheng, Wei Emma Zhang, Olaf Maennel +2

Mixture-of-Experts (MoE) presents a naturally compatible and scalable framework for multimodal learning, demonstrating strong adaptability across diverse modalities and tasks. Desp…

cs.LG2026

Rethinking Gating Mechanism in Sparse MoE: Handling Arbitrary Modality Inputs with Confidence-Guided Gate

Liangwei Nathan Zheng, Wei Emma Zhang, Mingyu Guo +2

Effectively managing missing modalities is a fundamental challenge in real-world multimodal learning scenarios, where data incompleteness often results from systematic collection e…

cs.LG2025

Lifting Manifolds to Mitigate Pseudo-Alignment in LLM4TS

Liangwei Nathan Zheng, Wenhao Liang, Wei Emma Zhang +3

Pseudo-Alignment is a pervasive challenge in many large language models for time series (LLM4TS) models, often causing them to underperform compared to linear models or randomly in…

cs.LG2025

Focal Calibration Loss: Controlling Posterior Distortion in Deep Neural Classifiers

Wenhao Liang, Chang Dong, Liangwei Zheng +2

Confidence calibration matters wherever a classifier's probabilities, not just its labels, are consumed downstream. We study Focal Calibration Loss (FCL), which adds a squared prob…

cs.LG2025

Understanding Why Large Language Models Can Be Ineffective in Time Series Analysis: The Impact of Modality Alignment

Liangwei Nathan Zheng, Chang George Dong, Wei Emma Zhang +4

Large Language Models (LLMs) have demonstrated impressive performance in time series analysis and seems to understand the time temporal relationship well than traditional transform…