Zedong Wang (Jacky)
@jackywang28.bsky.social
CSE PhD student at HKUST || Deep Learning, Computer Vision, Multi-task Learning, Multimodal Learning.
Homepage: https://jacky1128.github.io
📍Hong Kong 🇭🇰
Homepage: https://jacky1128.github.io
📍Hong Kong 🇭🇰
Reposted by Zedong Wang (Jacky)
Zedong Wang, Siyuan Li, Dan Xu: Rep-MTL: Unleashing the Power of Representation-level Task Saliency for Multi-Task Learning https://arxiv.org/abs/2507.21049 https://arxiv.org/pdf/2507.21049 https://arxiv.org/html/2507.21049
July 29, 2025 at 6:35 AM
Zedong Wang, Siyuan Li, Dan Xu: Rep-MTL: Unleashing the Power of Representation-level Task Saliency for Multi-Task Learning https://arxiv.org/abs/2507.21049 https://arxiv.org/pdf/2507.21049 https://arxiv.org/html/2507.21049
Golden hour never disappoints. 🌄
July 15, 2025 at 12:22 PM
Golden hour never disappoints. 🌄
Reposted by Zedong Wang (Jacky)
MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization
huggingface.co/papers/2504....
huggingface.co/papers/2504....
Paper page - MergeVQ: A Unified Framework for Visual Generation and Representation
with Disentangled Token Merging and Quantization
Join the discussion on this paper page
huggingface.co
April 3, 2025 at 11:30 AM
MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization
huggingface.co/papers/2504....
huggingface.co/papers/2504....
Reposted by Zedong Wang (Jacky)
Siyuan Li, Juanxi Tian, Zedong Wang, Xin Jin, Zicheng Liu, Wentao Zhang, Dan Xu: Taming LLMs by Scaling Learning Rates with Gradient Grouping https://arxiv.org/abs/2506.01049 https://arxiv.org/pdf/2506.01049 https://arxiv.org/html/2506.01049
June 3, 2025 at 6:26 AM
Siyuan Li, Juanxi Tian, Zedong Wang, Xin Jin, Zicheng Liu, Wentao Zhang, Dan Xu: Taming LLMs by Scaling Learning Rates with Gradient Grouping https://arxiv.org/abs/2506.01049 https://arxiv.org/pdf/2506.01049 https://arxiv.org/html/2506.01049