230 citations · 331 across the 19 of their papers we have counts for
20 papers
Thinking-while-speaking: A Controlled, Interleaved Reasoning Method for Real-Time Speech Generation
Xuan Du, Qiangyu Yan, Wenshuo Li +4
The thinking-while-speaking paradigm aims to make AI communication more human. A key challenge is maintaining fluent speech while performing deep reasoning. Our method, InterRS, ta…
SJD-PAC: Accelerating Speculative Jacobi Decoding via Proactive Drafting and Adaptive Continuation
Jialiang Kang, Han Shu, Wenshuo Li +2
Speculative Jacobi Decoding (SJD) offers a draft-model-free approach to accelerate autoregressive text-to-image synthesis. However, the high-entropy nature of visual generation yie…
Visual-textual Dermatoglyphic Animal Biometrics: A First Case Study on Panthera tigris
Wenshuo Li, Majid Mirmehdi, Tilo Burghardt
Biologists have long combined visuals with textual field notes to re-identify (Re-ID) animals. Contemporary AI tools automate this for species with distinctive morphological featur…
ViSpec: Accelerating Vision-Language Models with Vision-Aware Speculative Decoding
Jialiang Kang, Han Shu, Wenshuo Li +2
Speculative decoding is a widely adopted technique for accelerating inference in large language models (LLMs), yet its application to vision-language models (VLMs) remains underexp…
Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Model Enhancement
Qianhan Feng, Wenshuo Li, Tong Lin +1
Vision-Language Models (VLMs) bring powerful understanding and reasoning capabilities to multimodal tasks. Meanwhile, the great need for capable aritificial intelligence on mobile…
Full-Stage Pseudo Label Quality Enhancement for Weakly-supervised Temporal Action Localization
Qianhan Feng, Wenshuo Li, Tong Lin +1
Weakly-supervised Temporal Action Localization (WSTAL) aims to localize actions in untrimmed videos using only video-level supervision. Latest WSTAL methods introduce pseudo label…
ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking
Wenshuo Li, Xinghao Chen, Han Shu +2
Large language models (LLM) have recently attracted significant attention in the field of artificial intelligence. However, the training process of these models poses significant c…
No Time to Waste: Squeeze Time into Channel for Mobile Video Understanding
Yingjie Zhai, Wenshuo Li, Yehui Tang +2
Current architectures for video understanding mainly build upon 3D convolutional blocks or 2D convolutions with additional operations for temporal modeling. However, these methods…
TinySAM: Pushing the Envelope for Efficient Segment Anything Model
Han Shu, Wenshuo Li, Yehui Tang +5
Recently segment anything model (SAM) has shown powerful segmentation capability and has drawn great attention in computer vision fields. Massive following works have developed var…
CNN-transformer mixed model for object detection
Wenshuo Li
Object detection, one of the three main tasks of computer vision, has been used in various applications. The main process is to use deep neural networks to extract the features of…
Brain-inspired Multilayer Perceptron with Spiking Neurons
Wenshuo Li, Hanting Chen, Jianyuan Guo +2
Recently, Multilayer Perceptron (MLP) becomes the hotspot in the field of computer vision tasks. Without inductive bias, MLPs perform well on feature extraction and achieve amazing…
Winograd Algorithm for AdderNet
Wenshuo Li, Hanting Chen, Mingqiang Huang +3
Adder neural network (AdderNet) is a new kind of deep model that replaces the original massive multiplications in convolutions by additions while preserving the high performance. S…
Discovering Robust Convolutional Architecture at Targeted Capacity: A Multi-Shot Approach
Xuefei Ning, Junbo Zhao, Wenshuo Li +4
Convolutional neural networks (CNNs) are vulnerable to adversarial examples, and studies show that increasing the model capacity of an architecture topology (e.g., width expansion)…
aw_nas: A Modularized and Extensible NAS framework
Xuefei Ning, Changcheng Tang, Wenshuo Li +7
Neural Architecture Search (NAS) has received extensive attention due to its capability to discover neural network architectures in an automated manner. aw_nas is an open-source Py…
Physical Adversarial Attack on Vehicle Detector in the Carla Simulator
Tong Wu, Xuefei Ning, Wenshuo Li +3
In this paper, we tackle the issue of physical adversarial examples for object detectors in the wild. Specifically, we proposed to generate adversarial patterns to be applied on ve…
Evaluating Efficient Performance Estimators of Neural Architectures
Xuefei Ning, Changcheng Tang, Wenshuo Li +4
Conducting efficient performance estimations of neural architectures is a major challenge in neural architecture search (NAS). To reduce the architecture training costs in NAS, one…
DSA: More Efficient Budgeted Pruning via Differentiable Sparsity Allocation
Xuefei Ning, Tianchen Zhao, Wenshuo Li +3
Budgeted pruning is the problem of pruning under resource constraints. In budgeted pruning, how to distribute the resources across layers (i.e., sparsity allocation) is the key pro…
FTT-NAS: Discovering Fault-Tolerant Convolutional Neural Architecture
Xuefei Ning, Guangjun Ge, Wenshuo Li +6
With the fast evolvement of embedded deep-learning computing systems, applications powered by deep learning are moving from the cloud to the edge. When deploying neural networks (N…
Hu-Fu: Hardware and Software Collaborative Attack Framework against Neural Networks
Wenshuo Li, Jincheng Yu, Xuefei Ning +4
Recently, Deep Learning (DL), especially Convolutional Neural Network (CNN), develops rapidly and is applied to many tasks, such as image classification, face recognition, image se…
Exploring the Regularity of Sparse Structure in Convolutional Neural Networks
Huizi Mao, Song Han, Jeff Pool +4
Sparsity helps reduce the computational complexity of deep neural networks by skipping zeros. Taking advantage of sparsity is listed as a high priority in next generation DNN accel…