15 citations · 20 across the 12 of their papers we have counts for
12 papers
Think in Sets for Streaming Video Token Compression
Moxu Duan, Jingwen Fu, Yuwang Wang
Streaming VideoLLMs process frames causally while visual tokens grow continuously, making compression essential for controlling prefilling latency and memory. Existing training-fre…
Breakthrough the Suboptimal Stable Point in Value-Factorization-Based Multi-Agent Reinforcement Learning
Lesong Tao, Yifei Wang, Haodong Jing +4
Value factorization, a popular paradigm in MARL, faces significant theoretical and algorithmic bottlenecks: its tendency to converge to suboptimal solutions remains poorly understo…
A General Theory for Compositional Generalization
Jingwen Fu, Zhizheng Zhang, Yan Lu +1
Compositional Generalization (CG) embodies the ability to comprehend novel combinations of familiar concepts, representing a significant cognitive leap in human intellectual advanc…
Closing the Gap Between the Upper Bound and the Lower Bound of Adam's Iteration Complexity
Bohan Wang, Jingwen Fu, Huishuai Zhang +2
Recently, Arjevani et al. [1] established a lower bound of iteration complexity for the first-order optimization under an -smooth condition and a bounded noise variance assumpti…
Generalization error bounds for iterative learning algorithms with bounded updates
Jingwen Fu, Nanning Zheng
This paper explores the generalization characteristics of iterative learning algorithms with bounded updates for non-convex loss functions, employing information-theoretic techniqu…
Breaking through the learning plateaus of in-context learning in Transformer
Jingwen Fu, Tao Yang, Yuwang Wang +2
In-context learning, i.e., learning from context examples, is an impressive ability of Transformer. Training Transformers to possess this in-context learning skill is computational…
When and Why Momentum Accelerates SGD:An Empirical Study
Jingwen Fu, Bohan Wang, Huishuai Zhang +3
Momentum has become a crucial component in deep learning optimizers, necessitating a comprehensive understanding of when and why it accelerates stochastic gradient descent (SGD). T…
Learning Trajectories are Generalization Indicators
Jingwen Fu, Zhizheng Zhang, Dacheng Yin +2
This paper explores the connection between learning trajectories of Deep Neural Networks (DNNs) and their generalization capabilities when optimized using (stochastic) gradient des…
StructVPR: Distill Structural Knowledge with Weighting Samples for Visual Place Recognition
Yanqing Shen, Sanping Zhou, Jingwen Fu +3
Visual place recognition (VPR) is usually considered as a specific image retrieval problem. Limited by existing training frameworks, most deep learning-based works cannot extract s…
Understanding Mobile GUI: from Pixel-Words to Screen-Sentences
Jingwen Fu, Xiaoyi Zhang, Yuwang Wang +3
The ubiquity of mobile phones makes mobile GUI understanding an important task. Most previous works in this domain require human-created metadata of screens (e.g. View Hierarchy) d…
Model Adaption Object Detection System for Robot
Jingwen Fu, Licheng Zong, Yinbing Li +3
Object detection for robot guidance is a crucial mission for autonomous robots, which has provoked extensive attention for researchers. However, the changing view of robot movement…
Recognition Of Surface Defects On Steel Sheet Using Transfer Learning
Jingwen Fu, Xiaoyan Zhu, Yingbin Li
Automatic defect recognition is one of the research hotspots in steel production, but most of the current methods mainly extract features manually and use machine learning classifi…