66 citations · 179 across the 20 of their papers we have counts for
20 papers
Multi-Resolution Flow Matching: Training-Free Diffusion Acceleration via Staged Sampling
Xingyu Zheng, Xianglong Liu, Yifu Ding +4
Hardware-agnostic strategies for accelerating text-to-image diffusion, such as timestep distillation and feature caching, can reduce inference time without custom kernels or system…
MoDES: Accelerating Mixture-of-Experts Multimodal Large Language Models via Dynamic Expert Skipping
Yushi Huang, Zining Wang, Zhihang Yuan +5
Mixture-of-Experts (MoE) Multimodal large language models (MLLMs) excel at vision-language tasks, but they suffer from high computational inefficiency. To reduce inference overhead…
QVGen: Pushing the Limit of Quantized Video Generative Models
Yushi Huang, Ruihao Gong, Jing Liu +4
Video diffusion models (DMs) have enabled high-quality video synthesis. Yet, their substantial computational and memory demands pose serious challenges to real-world deployment, ev…
Dynamic Parallel Tree Search for Efficient LLM Reasoning
Yifu Ding, Wentao Jiang, Shunyu Liu +9
Tree of Thoughts (ToT) enhances Large Language Model (LLM) reasoning by structuring problem-solving as a spanning tree. However, recent methods focus on search accuracy while overl…
LLMCBench: Benchmarking Large Language Model Compression for Efficient Deployment
Ge Yang, Changyi He, Jinyang Guo +6
Although large language models (LLMs) have demonstrated their strong intelligence ability, the high demand for computation and storage hinders their practical application. To this…
A Survey of Low-bit Large Language Models: Basics, Systems, and Algorithms
Ruihao Gong, Yifu Ding, Zining Wang +7
Large language models (LLMs) have achieved remarkable advancements in natural language processing, showcasing exceptional performance across various tasks. However, the expensive m…
PTQ4SAM: Post-Training Quantization for Segment Anything
Chengtao Lv, Hong Chen, Jinyang Guo +2
Segment Anything Model (SAM) has achieved impressive performance in many computer vision tasks. However, as a large-scale model, the immense memory and computation costs hinder its…
DB-LLM: Accurate Dual-Binarization for Efficient LLMs
Hong Chen, Chengtao Lv, Liang Ding +8
Large language models (LLMs) have significantly advanced the field of natural language processing, while the expensive memory and computation consumption impede their practical dep…
On-Chip Hardware-Aware Quantization for Mixed Precision Neural Networks
Wei Huang, Haotong Qin, Yangdong Liu +4
Low-bit quantization emerges as one of the most promising compression approaches for deploying deep neural networks on edge devices. Mixed-precision quantization leverages a mixtur…
Towards Accurate Post-Training Quantization for Vision Transformer
Yifu Ding, Haotong Qin, Qinghua Yan +4
Vision transformer emerges as a potential architecture for vision tasks. However, the intense computation and non-negligible delay hinder its application in the real world. As a wi…
BiBench: Benchmarking and Analyzing Network Binarization
Haotong Qin, Mingyuan Zhang, Yifu Ding +5
Network binarization emerges as one of the most promising compression approaches offering extraordinary computation and memory savings by minimizing the bit-width. However, recent…
BiFSMNv2: Pushing Binary Neural Networks for Keyword Spotting to Real-Network Performance
Haotong Qin, Xudong Ma, Yifu Ding +6
Deep neural networks, such as the Deep-FSMN, have been widely studied for keyword spotting (KWS) applications while suffering expensive computation and storage. Therefore, network…
BiBERT: Accurate Fully Binarized BERT
Haotong Qin, Yifu Ding, Mingyuan Zhang +5
The large pre-trained BERT has achieved remarkable performance on Natural Language Processing (NLP) tasks but is also computation and memory expensive. As one of the powerful compr…
BiFSMN: Binary Neural Network for Keyword Spotting
Haotong Qin, Xudong Ma, Yifu Ding +6
The deep neural networks, such as the Deep-FSMN, have been widely studied for keyword spotting (KWS) applications. However, computational resources for these networks are significa…
Distribution-sensitive Information Retention for Accurate Binary Neural Network
Haotong Qin, Xiangguo Zhang, Ruihao Gong +3
Model binarization is an effective method of compressing neural networks and accelerating their inference process. However, a significant performance gap still exists between the 1…
Diverse Sample Generation: Pushing the Limit of Generative Data-free Quantization
Haotong Qin, Yifu Ding, Xiangguo Zhang +3
Generative data-free quantization emerges as a practical compression approach that quantizes deep neural networks to low bit-width without accessing the real data. This approach ge…
Multi-Pretext Attention Network for Few-shot Learning with Self-supervision
Hainan Li, Renshuai Tao, Jun Li +4
Few-shot learning is an interesting and challenging study, which enables machines to learn from few samples like humans. Existing studies rarely exploit auxiliary information from…
Diversifying Sample Generation for Accurate Data-Free Quantization
Xiangguo Zhang, Haotong Qin, Yifu Ding +6
Quantization has emerged as one of the most prevalent approaches to compress and accelerate neural networks. Recently, data-free quantization has been widely studied as a practical…
Over-sampling De-occlusion Attention Network for Prohibited Items Detection in Noisy X-ray Images
Renshuai Tao, Yanlu Wei, Hainan Li +4
Security inspection is X-ray scanning for personal belongings in suitcases, which is significantly important for the public security but highly time-consuming for human inspectors.…
BiPointNet: Binary Neural Network for Point Clouds
Haotong Qin, Zhongang Cai, Mingyuan Zhang +5
To alleviate the resource constraint for real-time point cloud applications that run on edge devices, in this paper we present BiPointNet, the first model binarization approach for…