2.2k citations · 3.3k across the 14 of their papers we have counts for
14 papers
LGViT: Dynamic Early Exiting for Accelerating Vision Transformer
Guanyu Xu, Jiawei Hao, Li Shen +4
Recently, the efficient deployment and acceleration of powerful vision transformers (ViTs) on resource-limited edge devices for providing multimedia services have become attractive…
Boosting Backdoor Attack with A Learnable Poisoning Sample Selection Strategy
Zihao Zhu, Mingda Zhang, Shaokui Wei +3
Data-poisoning based backdoor attacks aim to insert backdoor into models by manipulating training datasets without controlling the training process of the target model. Existing at…
Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimization
Mingli Zhu, Shaokui Wei, Li Shen +2
Backdoor defense, which aims to detect or mitigate the effect of malicious triggers introduced by attackers, is becoming increasingly critical for machine learning security and int…
Streaming Radiance Fields for 3D Video Synthesis
Lingzhi Li, Zhen Shen, Zhongshu Wang +2
We present an explicit-grid based method for efficiently reconstructing streaming radiance fields for novel view synthesis of real world dynamic scenes. Instead of training a singl…
Depth-Aware Generative Adversarial Network for Talking Head Video Generation
Fa-Ting Hong, Longhao Zhang, Li Shen +1
Talking head video generation aims to produce a synthetic human face video that contains the identity and pose information respectively from a given source image and a driving vide…
Learning Meta Representations for Agents in Multi-Agent Reinforcement Learning
Shenao Zhang, Li Shen, Lei Han
In multi-agent reinforcement learning, the behaviors that agents learn in a single Markov Game (MG) are typically confined to the given agent number. Every single MG induced by var…