96 citations · 233 across the 23 of their papers we have counts for
24 papers
DSDyn-VLA: A Dual-Stream Dynamic Manipulation Framework with Motion Perception, Future Awareness, and Realtime Correction
Wenhao Li, Xiu Su, Yu Han +3
While Vision-Language-Action (VLA) models excel in static tasks, they struggle in dynamic environments where objects are in motion (e.g., conveyor belt manipulation). We identify t…
VLA-ATTC: Adaptive Test-Time Compute for VLA Models with Relative Action Critic Model
Wenhao Li, Xiu Su, Yichao Cao +5
Vision-Language-Action (VLA) models have demonstrated remarkable capabilities and generalization in embodied manipulation. However, their decision-making relies on a fast, instinct…
Sentinel-VLA: A Metacognitive VLA Model with Active Status Monitoring for Dynamic Reasoning and Error Recovery
Wenhao Li, Xiu Su, Dan Niu +6
Vision-language-action (VLA) models have advanced the field of embodied manipulation by harnessing broad world knowledge and strong generalization. However, current VLA models stil…
Decoupled Video Generation with Chain of Training-free Diffusion Model Experts
Wenhao Li, Yichao Cao, Xiu Su +5
Video generation models hold substantial potential in areas such as filmmaking. However, current video diffusion models need high computational costs and produce suboptimal results…
LocalMamba: Visual State Space Model with Windowed Selective Scan
Tao Huang, Xiaohuan Pei, Shan You +3
Recent advancements in state space models, notably Mamba, have demonstrated significant progress in modeling long sequences for tasks like language understanding. Yet, their applic…
Active Generation for Image Classification
Tao Huang, Jiaqi Liu, Shan You +1
Recently, the growing capabilities of deep generative models have underscored their potential in enhancing image classification accuracy. However, existing methods often demand the…
Adaptive Training Meets Progressive Scaling: Elevating Efficiency in Diffusion Models
Wenhao Li, Xiu Su, Yu Han +3
Diffusion models have demonstrated remarkable efficacy in various generative tasks with the predictive prowess of denoising model. Currently, diffusion models employ a uniform deno…
Detecting Any Human-Object Interaction Relationship: Universal HOI Detector with Spatial Prompt Learning on Foundation Models
Yichao Cao, Qingfei Tang, Xiu Su +4
Human-object interaction (HOI) detection aims to comprehend the intricate relationships between humans and objects, predicting triplets, and serving as th…
DiffNAS: Bootstrapping Diffusion Models by Prompting for Better Architectures
Wenhao Li, Xiu Su, Shan You +3
Diffusion models have recently exhibited remarkable performance on synthetic data. After a diffusion path is selected, a base model, such as UNet, operates as a denoising autoencod…
CoNe: Contrast Your Neighbours for Supervised Image Classification
Mingkai Zheng, Shan You, Lang Huang +5
Image classification is a longstanding problem in computer vision and machine learning research. Most recent works (e.g. SupCon , Triplet, and max-margin) mainly focus on grouping…
SimMatchV2: Semi-Supervised Learning with Graph Consistency
Mingkai Zheng, Shan You, Lang Huang +4
Semi-Supervised image classification is one of the most fundamental problem in computer vision, which significantly reduces the need for human labor. In this paper, we introduce a…
Re-mine, Learn and Reason: Exploring the Cross-modal Semantic Correlations for Language-guided HOI detection
Yichao Cao, Qingfei Tang, Feng Yang +4
Human-Object Interaction (HOI) detection is a challenging computer vision task that requires visual models to address the complex interactive relationship between humans and object…
Knowledge Diffusion for Distillation
Tao Huang, Yuan Zhang, Mingkai Zheng +4
The representation gap between teacher and student is an emerging topic in knowledge distillation (KD). To reduce the gap and improve the performance, current methods often resort…
Can GPT-4 Perform Neural Architecture Search?
Mingkai Zheng, Xiu Su, Shan You +4
We investigate the potential of GPT-4~\cite{gpt4} to perform Neural Architecture Search (NAS) -- the task of designing effective neural architectures. Our proposed approach, \textb…
LightViT: Towards Light-Weight Convolution-Free Vision Transformers
Tao Huang, Lang Huang, Shan You +3
Vision transformers (ViTs) are usually considered to be less light-weight than convolutional neural networks (CNNs) due to the lack of inductive bias. Recent works thus resort to c…
Masked Distillation with Receptive Tokens
Tao Huang, Yuan Zhang, Shan You +4
Distilling from the feature maps can be fairly effective for dense prediction tasks since both the feature discriminability and localization priors can be well transferred. However…
Knowledge Distillation from A Stronger Teacher
Tao Huang, Shan You, Fei Wang +2
Unlike existing knowledge distillation methods focus on the baseline settings, where the teacher models and training strategies are not that strong and competing as state-of-the-ar…
Searching for Network Width with Bilaterally Coupled Network
Xiu Su, Shan You, Jiyang Xie +4
Searching for a more compact network width recently serves as an effective way of channel pruning for the deployment of convolutional neural networks (CNNs) under hardware constrai…
DyRep: Bootstrapping Training with Dynamic Re-parameterization
Tao Huang, Shan You, Bohan Zhang +4
Structural re-parameterization (Rep) methods achieve noticeable improvements on simple VGG-style networks. Despite the prevalence, current Rep methods simply re-parameterize all op…
SimMatch: Semi-supervised Learning with Similarity Matching
Mingkai Zheng, Shan You, Lang Huang +3
Learning with few labeled data has been a longstanding problem in the computer vision and machine learning research community. In this paper, we introduced a new semi-supervised le…
Weak Augmentation Guided Relational Self-Supervised Learning
Mingkai Zheng, Shan You, Fei Wang +4
Self-supervised Learning (SSL) including the mainstream contrastive learning has achieved great success in learning visual representations without data annotations. However, most m…
Relational Surrogate Loss Learning
Tao Huang, Zekang Li, Hua Lu +6
Evaluation metrics in machine learning are often hardly taken as loss functions, as they could be non-differentiable and non-decomposable, e.g., average precision and F1 score. Thi…
GreedyNASv2: Greedier Search with a Greedy Path Filter
Tao Huang, Shan You, Fei Wang +4
Training a good supernet in one-shot NAS methods is difficult since the search space is usually considerably huge (e.g., ). In order to enhance the supernet's evaluation a…
ViTAS: Vision Transformer Architecture Search
Xiu Su, Shan You, Jiyang Xie +6
Vision transformers (ViTs) inherited the success of NLP but their structures have not been sufficiently investigated and optimized for visual tasks. One of the simplest solutions i…