144 citations · 432 across the 16 of their papers we have counts for
17 papers
VLMimic: Vision Language Models are Visual Imitation Learner for Fine-grained Actions
Guanyan Chen, Meiling Wang, Te Cui +9
Visual imitation learning (VIL) provides an efficient and intuitive strategy for robotic systems to acquire novel skills. Recent advancements in Vision Language Models (VLMs) have…
Chatlaw: A Multi-Agent Legal Assistant based on a Role-Aligned Mixture-of-Experts Architecture
Jiaxi Cui, Munan Ning, Zongjian Li +6
Artificial Intelligence (AI) holds great potential in legal services, yet Large Language Models (LLMs) face two major challenges: limited knowledge of the Chinese legal system and…
PointGPT: Auto-regressively Generative Pre-training from Point Clouds
Guangyan Chen, Meiling Wang, Yi Yang +3
Large language models (LLMs) based on the generative pre-training transformer (GPT) have demonstrated remarkable effectiveness across a diverse range of downstream tasks. Inspired…
Full Transformer Framework for Robust Point Cloud Registration with Deep Information Interaction
Guangyan Chen, Meiling Wang, Yufeng Yue +2
Recent Transformer-based methods have achieved advanced performance in point cloud registration by utilizing advantages of the Transformer in order-invariance and modeling dependen…
VOLO: Vision Outlooker for Visual Recognition
Li Yuan, Qibin Hou, Zihang Jiang +2
Visual recognition has been dominated by convolutional neural networks (CNNs) for years. Though recently the prevailing vision transformers (ViTs) have shown great potential of sel…
Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition
Qibin Hou, Zihang Jiang, Li Yuan +3
In this paper, we present Vision Permutator, a conceptually simple and data efficient MLP-like architecture for visual recognition. By realizing the importance of the positional in…
Continual Learning via Bit-Level Information Preserving
Yujun Shi, Li Yuan, Yunpeng Chen +1
Continual learning tackles the setting of learning different tasks sequentially. Despite the lots of previous solutions, most of them still suffer significant forgetting or expensi…
All Tokens Matter: Token Labeling for Training Better Vision Transformers
Zihang Jiang, Qibin Hou, Li Yuan +5
In this paper, we present token labeling -- a new training objective for training high-performance vision transformers (ViTs). Different from the standard training objective of ViT…
Positive-Negative Momentum: Manipulating Stochastic Gradient Noise to Improve Generalization
Zeke Xie, Li Yuan, Zhanxing Zhu +1
It is well-known that stochastic gradient noise (SGN) acts as implicit regularization for deep learning and is essentially important for both optimization and generalization of dee…
Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
Li Yuan, Yunpeng Chen, Tao Wang +6
Transformers, which are popular for language modeling, have been explored for solving vision tasks recently, e.g., the Vision Transformer (ViT) for image classification. The ViT mo…
Fooling the primate brain with minimal, targeted image manipulation
Li Yuan, Will Xiao, Giorgia Dellaferrera +4
Artificial neural networks (ANNs) are considered the current best models of biological vision. ANNs are the best predictors of neural activity in the ventral stream; moreover, rece…
Revisiting Knowledge Distillation via Label Smoothing Regularization
Li Yuan, Francis E. H. Tay, Guilin Li +2
Knowledge Distillation (KD) aims to distill the knowledge of a cumbersome teacher model into a lightweight student model. Its success is generally attributed to the privileged info…
Modular Deep Reinforcement Learning with Temporal Logic Specifications
Lim Zun Yuan, Mohammadhosein Hasanbeig, Alessandro Abate +1
We propose an actor-critic, model-free, and online Reinforcement Learning (RL) framework for continuous-state continuous-action Markov Decision Processes (MDPs) when the reward is…
Central Similarity Quantization for Efficient Image and Video Retrieval
Li Yuan, Tao Wang, Xiaopeng Zhang +4
Existing data-dependent hashing methods usually learn hash functions from pairwise or triplet data relationships, which only capture the data similarity locally, and often suffer f…
Distilling Object Detectors with Fine-grained Feature Imitation
Tao Wang, Li Yuan, Xiaopeng Zhang +1
State-of-the-art CNN based recognition models are often computationally prohibitive to deploy on low-end devices. A promising high level approach tackling this limitation is knowle…
Cycle-SUM: Cycle-consistent Adversarial LSTM Networks for Unsupervised Video Summarization
Li Yuan, Francis EH Tay, Ping Li +2
In this paper, we present a novel unsupervised video summarization model that requires no manual annotation. The proposed model termed Cycle-SUM adopts a new cycle-consistent adver…
Few-shot Adaptive Faster R-CNN
Tao Wang, Xiaopeng Zhang, Li Yuan +1
To mitigate the detection performance drop caused by domain shift, we aim to develop a novel few-shot adaptation approach that requires only a few target domain images with limited…