Ioannis Patras

Full Professor@Queen Mary, University of London·英国·OpenReview

研究方向

Machine unlearning · Multimodal AI · Video generation · Video Understanding · Large Multimodal models · Affective Computing · EEG · Deep Learning · computer vision · deep learning · action recognition · facial expression recognition

6.0

Beyond Linear Probes: Dynamic Safety Monitoring for Language Models

ICLR 2026Poster

三作

4.5

Latent Reward-Guided Search for Faster Inference-Time Scaling in Video Diffusion

ICLR 2026Rejected

通讯

3.5

Is the Prediction Set Size Well-Calibrated? A Closer Look at Uncertainty in Conformal Prediction

ICLR 2026Withdrawn

8.2

Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders

NeurIPS 2025Poster

7.3

$\boldsymbol{\lambda}$-Orthogonality Regularization for Compatible Representation Learning

NeurIPS 2025Poster

4.7

Towards Better Understanding Open-set Noise in Learning with Noisy Labels

ICLR 2025Rejected

三作

4.0

FairCoT: Enhancing Fairness in Diffusion Models via Chain of Thought Reasoning of Multimodal Language Models

合作者 (20)