411 citations · 887 across the 22 of their papers we have counts for
22 papers
VisionLLaMA: A Unified LLaMA Backbone for Vision Tasks
Xiangxiang Chu, Jianlin Su, Bo Zhang +1
Large language models are built on top of a transformer-based architecture to process textual inputs. For example, the LLaMA stands out among many open-source implementations. Can…
MobileVLM V2: Faster and Stronger Baseline for Vision Language Model
Xiangxiang Chu, Limeng Qiao, Xinyu Zhang +8
We introduce MobileVLM V2, a family of significantly improved vision language models upon MobileVLM, which proves that a delicate orchestration of novel architectural design, an im…
LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection
Sifan Zhou, Liang Li, Xinyu Zhang +6
Due to highly constrained computing power and memory, deploying 3D lidar-based detectors on edge devices equipped in autonomous vehicles and robots poses a crucial challenge. Being…
MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices
Xiangxiang Chu, Limeng Qiao, Xinyang Lin +8
We present MobileVLM, a competent multimodal vision language model (MMVLM) targeted to run on mobile devices. It is an amalgamation of a myriad of architectural designs and techniq…
Lenna: Language Enhanced Reasoning Detection Assistant
Fei Wei, Xinyu Zhang, Ailing Zhang +2
With the fast-paced development of multimodal large language models (MLLMs), we can now converse with AI systems in natural languages to understand images. However, the reasoning p…
A Speed Odyssey for Deployable Quantization of LLMs
Qingyuan Li, Ran Meng, Yiduo Li +6
The large language model era urges faster and less costly inference. Prior model compression works on LLMs tend to undertake a software-centric approach primarily focused on the si…
Robust MAE-Driven NAS: From Mask Reconstruction to Architecture Innovation
Yiming Hu, Xiangxiang Chu, Yong Wang
Neural Architecture Search (NAS) relies heavily on labeled data, which is labor-intensive and time-consuming to obtain. In this paper, we propose a novel NAS method based on an uns…
Norm Tweaking: High-performance Low-bit Quantization of Large Language Models
Liang Li, Qingyuan Li, Bo Zhang +1
As the size of large language models (LLMs) continues to grow, model compression without sacrificing accuracy has become a crucial challenge for deployment. While some quantization…
FPTQ: Fine-grained Post-Training Quantization for Large Language Models
Qingyuan Li, Yifan Zhang, Liang Li +6
In the era of large-scale language models, the substantial parameter size poses significant challenges for deployment. Being a prevalent compression technique, quantization has eme…
FastPillars: A Deployment-friendly Pillar-based 3D Detector
Sifan Zhou, Zhi Tian, Xiangxiang Chu +7
The deployment of 3D detectors strikes one of the major challenges in real-world self-driving scenarios. Existing BEV-based (i.e., Bird Eye View) detectors favor sparse convolution…
YOLOv6 v3.0: A Full-Scale Reloading
Chuyi Li, Lulu Li, Yifei Geng +6
The YOLO community has been in high spirits since our first two releases! By the advent of Chinese New Year 2023, which sees the Year of the Rabbit, we refurnish YOLOv6 with numero…
Make RepVGG Greater Again: A Quantization-aware Approach
Xiangxiang Chu, Liang Li, Bo Zhang
The tradeoff between performance and inference speed is critical for practical applications. Architecture reparameterization obtains better tradeoffs and it is becoming an increasi…
EAPruning: Evolutionary Pruning for Vision Transformers and CNNs
Qingyuan Li, Bo Zhang, Xiangxiang Chu
Structured pruning greatly eases the deployment of large neural networks in resource-constrained environments. However, current methods either involve strong domain expertise, requ…
Conditional Positional Encodings for Vision Transformers
Xiangxiang Chu, Zhi Tian, Bo Zhang +2
We propose a conditional positional encoding (CPE) scheme for vision Transformers. Unlike previous fixed or learnable positional encodings, which are pre-defined and independent of…
A Unified Mixture-View Framework for Unsupervised Representation Learning
Xiangxiang Chu, Xiaohang Zhan, Bo Zhang
Recent unsupervised contrastive representation learning follows a Single Instance Multi-view (SIM) paradigm where positive pairs are usually constructed with intra-image data augme…
ROME: Robustifying Memory-Efficient NAS via Topology Disentanglement and Gradient Accumulation
Xiaoxing Wang, Xiangxiang Chu, Yuda Fan +4
Albeit being a prevalent architecture searching approach, differentiable architecture search (DARTS) is largely hindered by its substantial memory cost since the entire supernet re…
AutoKWS: Keyword Spotting with Differentiable Architecture Search
Bo Zhang, Wenfeng Li, Qingyuan Li +3
Smart audio devices are gated by an always-on lightweight keyword spotting program to reduce power consumption. It is however challenging to design models that have both high accur…
DARTS-: Robustly Stepping out of Performance Collapse Without Indicators
Xiangxiang Chu, Xiaoxing Wang, Bo Zhang +3
Despite the fast development of differentiable architecture search (DARTS), it suffers from long-standing performance instability, which extremely limits its application. Existing…
MoGA: Searching Beyond MobileNetV3
Xiangxiang Chu, Bo Zhang, Ruijun Xu
The evolution of MobileNets has laid a solid foundation for neural network applications on mobile end. With the latest MobileNetV3, neural architecture search again claimed its sup…
FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Search
Xiangxiang Chu, Bo Zhang, Ruijun Xu
One of the most critical problems in weight-sharing neural architecture search is the evaluation of candidate models within a predefined search space. In practice, a one-shot super…
A Matrix-in-matrix Neural Network for Image Super Resolution
Hailong Ma, Xiangxiang Chu, Bo Zhang +1
In recent years, deep learning methods have achieved impressive results with higher peak signal-to-noise ratio in single image super-resolution (SISR) tasks by utilizing deeper lay…
Fast, Accurate and Lightweight Super-Resolution with Neural Architecture Search
Xiangxiang Chu, Bo Zhang, Hailong Ma +2
Deep convolutional neural networks demonstrate impressive results in the super-resolution domain. A series of studies concentrate on improving peak signal noise ratio (PSNR) by usi…