Wenbo Hu's Homepage (胡文波)
 |
Email: hwb13 [AT] tsinghua [DOT] org [DOT] cn |
About
Associate Professor, School of Computer Science and Information Engineering, Hefei University of Technology
My research focuses on statistical machine learning, particularly trustworthy machine learning, including uncertainty quantification, adversarial robustness, and causality. My application interests include time series analysis, computer vision, and natural language processing.
[Selected Papers] [Selected Talks & Tutorials]
News!
[Tutorial] I will give a tutorial on Uncertainty and Calibration in Large Models – Reliable Reasoning and Agent Safety at CNCC 2026 on October 21, 2026. (Oct/26)
[Paper] Our paper Visual EQA-CL: A Continual Learning Task for Embodied Question Answering has been accepted for publication in Multimedia Systems. (Sep/26)
[Preprint] We have substantially revised our preprint Resolving sources of uncertainty in AI weather forecasting and released the model and code. (Sep/26)
[Paper] Our paper Visual Token Compression Enhances Robustness of MLLMs has been accepted at ACM MM 2026. See you in Brazil! (Jul/26)
[Talk] I gave a talk titled Trustworthiness, Robustness, and Evaluation of Multimodal Large Language Models at Huawei Noah's Ark Lab. (Feb/26)
[Paper] Our paper ProSafePrune: Projected Safety Pruning for Mitigating Over-Refusal in LLMs has been accepted at ICLR 2026. See you in Brazil! (Jan/26)
[Preprint] Our preprint Bridging the Gap Between Bayesian Deep Learning and Ensemble Weather Forecasts is now available online. (Nov/25)
[Paper] Three of our papers have been accepted at AAAI 2026. See you in Singapore! (Nov/25)
Selected Papers
Unveiling Uncertainty: A Deep Dive into Calibration and Performance of Multimodal Large Language Models – COLING 2025.
We investigate how well multimodal models assess their own uncertainty and improve calibration through temperature scaling and prompt optimization.
[Paper] [Code]
Deep Hidden Cognition Facilitates Reliable Chain-of-Thought Reasoning – AAAI 2026.
We use truthfulness-sensitive internal activations to estimate step-level confidence and guide more reliable chain-of-thought search.
[Paper] [Code]
ProSafePrune: Projected Safety Pruning for Mitigating Over-Refusal in LLMs – ICLR 2026.
We reduce over-refusal through subspace-projected low-rank pruning while preserving refusal of genuinely harmful requests.
[Paper] [Code]
Visual Token Compression Enhances Robustness of MLLMs – ACM MM 2026.
We prune misaligned visual tokens to improve robustness against jailbreaks and hallucinations while reducing inference cost.
[Paper] [Code]
Resolving sources of uncertainty in AI weather forecasting (Pangu-Bayes) – Preprint, updated September 2026.
We model atmospheric-state and learned-model uncertainty separately to study their different roles in tropical cyclone track and intensity prediction.
[Paper] [Code] [Model]
Selected Talks & Tutorials
Uncertainty and Calibration in Large Models – Reliable Reasoning and Agent Safety
CNCC 2026 Tutorial, October 21, 2026 (upcoming).
An introduction to uncertainty quantification and calibration, with applications to reliable reasoning and agent safety.
[Slides] [Program]
Trustworthiness, Robustness, and Evaluation of Multimodal Large Language Models
Huawei Noah's Ark Lab, February 2026.
A research talk on the reliability, adversarial robustness, and evaluation of multimodal large language models.
[Slides]