30 citations · 35 across the 5 of their papers we have counts for
5 papers
DUMP: Automated Distribution-Level Curriculum Learning for RL-based LLM Post-training
Zhenting Wang, Guofeng Cui, Yu-Jhe Li +2
Recent advances in reinforcement learning (RL)-based post-training have led to notable improvements in large language models (LLMs), particularly in enhancing their reasoning capab…
Talking-head Generation with Rhythmic Head Motion
Lele Chen, Guofeng Cui, Celong Liu +4
When people deliver a speech, they naturally move heads, and this rhythmic head motion conveys prosodic information. However, generating a lip-synced video while moving head natura…
What comprises a good talking-head video generation?: A Survey and Benchmark
Lele Chen, Guofeng Cui, Ziyi Kou +2
Over the years, performance evaluation has become essential in computer vision, enabling tangible progress in many sub-fields. While talking-head video generation has become an eme…
Improve CAM with Auto-adapted Segmentation and Co-supervised Augmentation
Ziyi Kou, Guofeng Cui, Shaojie Wang +2
Weakly Supervised Object Localization (WSOL) methods generate both classification and localization results by learning from only image category labels. Previous methods usually uti…
Weakly Supervised Localization Using Background Images
Ziyi Kou, Wentian Zhao, Guofeng Cui +1
Weakly Supervised Object Localization (WSOL) methodsusually rely on fully convolutional networks in order to ob-tain class activation maps(CAMs) of targeted labels. How-ever, these…