Yujiang Wang

Orcid: 0000-0002-6220-029X

Affiliations:

Imperial College London, London, UK

According to our database¹, Yujiang Wang authored at least 42 papers between 2017 and 2026.

Collaborative distances:

Dijkstra number² of four.
Erdős number³ of four.

Timeline

Legend:

Book In proceedings Article PhD thesis Dataset Other

Bibliography

2026

The Curse and Blessing of Mean Bias in FP4-Quantized LLM Training.

[BibT_eX]

[DOI]

CoRR, March, 2026

Multi-Head Attention as a Source of Catastrophic Forgetting in MoE Transformers.

[BibT_eX]

[DOI]

CoRR, February, 2026

SD-MoE: Spectral Decomposition for Effective Expert Specialization.

[BibT_eX]

[DOI]

CoRR, February, 2026

Spectra: Rethinking Optimizers for LLMs Under Spectral Anisotropy.

[BibT_eX]

[DOI]

CoRR, February, 2026

Dispelling the Curse of Singularities in Neural Network Optimizations.

[BibT_eX]

[DOI]

CoRR, February, 2026

2025

ActiveEye: Enabling Continuous and Responsive Video Understanding for Smart Eyewear Systems.

[BibT_eX]

[DOI]

Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., December, 2025

Efficient Task Grouping Through Sample-Wise Optimisation Landscape Analysis.

[BibT_eX]

[DOI]

IEEE Trans. Pattern Anal. Mach. Intell., October, 2025

Denoising Reuse: Exploiting Inter-Frame Motion Consistency for Efficient Video Generation.

[BibT_eX]

[DOI]

IEEE Trans. Circuits Syst. Video Technol., September, 2025

Metis: Training LLMs with FP4 Quantization.

[BibT_eX]

[DOI]

CoRR, September, 2025

FP-Age: Leveraging Face Parsing Attention for Facial Age Estimation in the Wild.

[BibT_eX]

[DOI]

IEEE Trans. Image Process., 2025

Oracle-MoE: Locality-preserving Routing in the Oracle Space for Memory-constrained Large Language Model Inference.

[BibT_eX]

[DOI]

Proceedings of the Forty-second International Conference on Machine Learning, 2025

2024

Can Large Language Models Be Good Companions?: An LLM-Based Eyewear System with Conversational Common Ground.

[BibT_eX]

[DOI]

Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., May, 2024

Efficient Task Grouping Through Samplewise Optimisation Landscape Analysis.

[BibT_eX]

[DOI]

CoRR, 2024

Denoising Reuse: Exploiting Inter-frame Motion Consistency for Efficient Video Latent Generation.

[BibT_eX]

[DOI]

CoRR, 2024

Once Read is Enough: Domain-specific Pretraining-free Language Models with Cluster-guided Sparse Experts for Long-tail Domain Knowledge.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

2023

Self-Supervised Video-Centralised Transformer for Video Face Clustering.

[BibT_eX]

[DOI]

IEEE Trans. Pattern Anal. Mach. Intell., November, 2023

Can Large Language Models Be Good Companions? An LLM-Based Eyewear System with Conversational Common Ground.

[BibT_eX]

[DOI]

CoRR, 2023

Is dataset condensation a silver bullet for healthcare data sharing?

[BibT_eX]

[DOI]

CoRR, 2023

Data Encoding For Healthcare Data Democratisation and Information Leakage Prevention.

[BibT_eX]

[DOI]

CoRR, 2023

Train Faster, Perform Better: Modular Adaptive Training in Over-Parameterized Models.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Over-parameterized Model Optimization with Polyak-Łojasiewicz Condition.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

A Reinforcement-Learning-Based Energy-Efficient Framework for Multi-Task Video Analytics Pipeline.

[BibT_eX]

[DOI]

IEEE Trans. Multim., 2022

Unveiling Causal Attention in Dogs' Eyes with Smart Eyewear.

[BibT_eX]

[DOI]

Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., 2022

Do Smart Glasses Dream of Sentimental Visions?: Deep Emotionship Analysis for Eyewear Devices.

[BibT_eX]

[DOI]

Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., 2022

Recursive Disentanglement Network.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

Training Strategies for Improved Lip-Reading.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2022

2021

Dynamic face parsing in the wild

[BibT_eX]

[DOI]

Yujiang Wang

PhD thesis, 2021

RoI Tanh-polar transformer network for face parsing in the wild.

[BibT_eX]

[DOI]

Image Vis. Comput., 2021

MemX: An Attention-Aware Smart Eyewear System for Personalized Moment Auto-capture.

[BibT_eX]

[DOI]

Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., 2021

Domain Generalisation for Apparent Emotional Facial Expression Recognition across Age-Groups.

[BibT_eX]

[DOI]

CoRR, 2021

Lip-reading with Densely Connected Temporal Convolutional Networks.

[BibT_eX]

[DOI]

Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 2021

2020

End-to-end visual speech recognition for small-scale datasets.

[BibT_eX]

[DOI]

Pattern Recognit. Lett., 2020

Learning Local Metrics and Influential Regions for Classification.

[BibT_eX]

[DOI]

IEEE Trans. Pattern Anal. Mach. Intell., 2020

Dilated Convolutions with Lateral Inhibitions for Semantic Image Segmentation.

[BibT_eX]

[DOI]

CoRR, 2020

Shape Constrained Network for Eye Segmentation in the Wild.

[BibT_eX]

[DOI]

Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 2020

Generalization Bound of Gradient Descent for Non-Convex Metric Learning.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Dynamic Face Video Segmentation via Reinforcement Learning.

[BibT_eX]

[DOI]

Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

2019

A real-time and unsupervised face re-identification system for human-robot interaction.

[BibT_eX]

[DOI]

Pattern Recognit. Lett., 2019

Face Mask Extraction in Video Sequence.

[BibT_eX]

[DOI]

Int. J. Comput. Vis., 2019

2018

The iBUG Eye Segmentation Dataset.

[BibT_eX]

[DOI]

Proceedings of the 2018 Imperial College Computing Student Workshop, 2018

2017

End-to-End Multi-View Lipreading.

[BibT_eX]

[DOI]

Proceedings of the British Machine Vision Conference 2017, 2017

End-to-End Audiovisual Fusion with LSTMs.

[BibT_eX]

[DOI]

Proceedings of the 14th International Conference on Auditory-Visual Speech Processing, 2017

Yujiang Wang

Timeline

Legend:

Links

Online presence:

On csauthors.net:

Bibliography

Loading...