1 citations · 2 across the 11 of their papers we have counts for
8 papers · 1 filter
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…
Auditing Routing Entropy as an Uncertainty Signal in Attention-Residual Transformers
Wenhao Liang, Lin Yue, Wei Emma Zhang +3
Dynamic architectures leave a per-example routing trace beside each prediction, and diffuse routing is easy to read as a sign that the prediction is unreliable. We audit that readi…
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…
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…
Probing Routing-Conditional Calibration in Attention-Residual Transformers
Wenhao Liang, Lin Yue, Wei Emma Zhang +4
Post-hoc calibration is usually evaluated as a function of logits or softmax confidence alone, even as routing-augmented architectures increasingly accompany predictions with sampl…
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…