5 citations · 9 across the 17 of their papers we have counts for
24 papers
TWIN-MoE: Two-stage Intra-Expert Imputation Network for Incomplete Multimodal Learning
Liang Nathan Zheng, Jiyuan Liu, Wenhao Liang +3
Recent Mixture-of-Experts (MoE) approaches address missing modalities either by routing each missingness pattern to a dedicated expert, which scales poorly as the number of modalit…
Detecting Chain-of-Thought Hijacking in Backdoored Multimodal Large Reasoning Models
Zhifang Zhang, Qi Wei, Weitong Chen +5
Chain-of-thought (CoT) reasoning enables multimodal large reasoning models (MLRMs) to solve complex visual problems, but also exposes them to CoT hijacking: an adversary implants a…
Spatial Supervision Without Attribution Optimization: Improving Post-Hoc Class Activation Maps via Box-Guided Evidence Routing
Wenhao Liang, Liangwei Nathan Zheng, Lin Yue +3
Post-hoc class activation maps (CAMs) are a standard tool for inspecting the evidence behind an image classifier's predictions, yet nothing in ordinary training encourages these ma…
Routing Probes Can Improve Without New Information: An Exact-Null Audit of Uncertainty Beyond Model Outputs
Wenhao Liang, Lin Yue, Wei Emma Zhang +3
Routing signals of modern vision transformers -- expert gates, attention-residual weights and halting scores -- often improve probes that predict whether the model is correct, and…
Signal-Routed Temperature Scaling: Low-Capacity Risk-Conditioned Calibration for Small Validation Budgets
Wenhao Liang, Liangwei Nathan Zheng, Lin Yue +4
When a classifier is recalibrated from only a few thousand held-out examples, the capacity of the calibration map becomes a statistical design choice rather than a purely architect…
How Much Can Reliability Drift Under a Fixed Confidence Distribution?
Wenhao Liang, Lin Yue, Wei Emma Zhang +3
A classifier's conditional accuracy can change while its confidence distribution stays exactly the same. We study the worst-case movement of the reliability relation under covariat…
Test-Time Attention Purification for Backdoored Large Vision Language Models
Zhifang Zhang, Bojun Yang, Shuo He +5
Despite the strong multimodal performance, large vision-language models (LVLMs) are vulnerable during fine-tuning to backdoor attacks, where adversaries insert trigger-embedded sam…
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…
Calibration Attention: Learning Reliability-Aware Representations for Vision Transformers
Wenhao Liang, Wei Emma Zhang, Lin Yue +4
Most calibration methods operate at the logit level, implicitly assuming that miscalibration can be corrected without changing the underlying representation. We challenge this assu…
FedDPG: An Adaptive Yet Efficient Prompt-tuning Approach in Federated Learning Settings
Ali Shakeri, Wei Emma Zhang, Amin Beheshti +3
Pre-trained Language Models (PLMs) have demonstrated impressive performance in various NLP tasks. However, traditional fine-tuning methods for leveraging PLMs for downstream tasks…
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…
MMiC: Mitigating Modality Incompleteness in Clustered Federated Learning
Lishan Yang, Wei Emma Zhang, Quan Z. Sheng +3
In the era of big data, data mining has become indispensable for uncovering hidden patterns and insights from vast and complex datasets. The integration of multimodal data sources…
PostHoc FREE Calibrating on Kolmogorov Arnold Networks
Wenhao Liang, Wei Emma Zhang, Lin Yue +3
Kolmogorov Arnold Networks (KANs) are neural architectures inspired by the Kolmogorov Arnold representation theorem that leverage B Spline parameterizations for flexible, locally a…
We Care Each Pixel: Calibrating on Medical Segmentation Model
Wenhao Liang, Wei Zhang, Lin Yue +3
Medical image segmentation is fundamental for computer-aided diagnostics, providing accurate delineation of anatomical structures and pathological regions. While common metrics suc…
TrojanTime: Backdoor Attacks on Time Series Classification
Chang Dong, Zechao Sun, Guangdong Bai +3
Time Series Classification (TSC) is highly vulnerable to backdoor attacks, posing significant security threats. Existing methods primarily focus on data poisoning during the traini…
Free-Knots Kolmogorov-Arnold Network: On the Analysis of Spline Knots and Advancing Stability
Liangwewi Nathan Zheng, Wei Emma Zhang, Lin Yue +3
Kolmogorov-Arnold Neural Networks (KANs) have gained significant attention in the machine learning community. However, their implementation often suffers from poor training stabili…
Irregularity-Informed Time Series Analysis: Adaptive Modelling of Spatial and Temporal Dynamics
Liangwei Nathan Zheng, Zhengyang Li, Chang George Dong +5
Irregular Time Series Data (IRTS) has shown increasing prevalence in real-world applications. We observed that IRTS can be divided into two specialized types: Natural Irregular Tim…
Devil in the Tail: A Multi-Modal Framework for Drug-Drug Interaction Prediction in Long Tail Distinction
Liangwei Nathan Zheng, Chang George Dong, Wei Emma Zhang +3
Drug-drug interaction (DDI) identification is a crucial aspect of pharmacology research. There are many DDI types (hundreds), and they are not evenly distributed with equal chance…
Focal Calibration Loss: Controlling Posterior Distortion in Deep Neural Classifiers
Wenhao Liang, Liangwei Zheng, Wei Zhang +1
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…
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…
Boosting Certified Robustness for Time Series Classification with Efficient Self-Ensemble
Chang Dong, Zhengyang Li, Liangwei Zheng +2
Recently, the issue of adversarial robustness in the time series domain has garnered significant attention. However, the available defense mechanisms remain limited, with adversari…
Kolmogorov-Arnold Networks (KAN) for Time Series Classification and Robust Analysis
Chang Dong, Liangwei Zheng, Weitong Chen
Kolmogorov-Arnold Networks (KAN) has recently attracted significant attention as a promising alternative to traditional Multi-Layer Perceptrons (MLP). Despite their theoretical app…
A Survey of Deep Learning-based Radiology Report Generation Using Multimodal Data
Xinyi Wang, Grazziela Figueredo, Ruizhe Li +3
Automatic radiology report generation can alleviate the workload for physicians and minimize regional disparities in medical resources, therefore becoming an important topic in the…
SWAP: Exploiting Second-Ranked Logits for Adversarial Attacks on Time Series
Chang George Dong, Liangwei Nathan Zheng, Weitong Chen +2
Time series classification (TSC) has emerged as a critical task in various domains, and deep neural models have shown superior performance in TSC tasks. However, these models are v…