12 papers
BiVM: Accurate Binarized Neural Network for Efficient Video Matting
Haotong Qin, Xianglong Liu, Xudong Ma +4
Deep neural networks for real-time video matting suffer significant computational limitations on edge devices, hindering their adoption in widespread applications such as online co…
MPQ-DMv2: Flexible Residual Mixed Precision Quantization for Low-Bit Diffusion Models with Temporal Distillation
Weilun Feng, Chuanguang Yang, Haotong Qin +10
Diffusion models have demonstrated remarkable performance on vision generation tasks. However, the high computational complexity hinders its wide application on edge devices. Quant…
First-Order Error Matters: Accurate Compensation for Quantized Large Language Models
Xingyu Zheng, Haotong Qin, Yuye Li +5
Post-training quantization (PTQ) offers an efficient approach to compressing large language models (LLMs), significantly reducing memory access and computational costs. Existing co…
Post-Training Quantization for Video Matting
Tianrui Zhu, Houyuan Chen, Ruihao Gong +3
Video matting is crucial for applications such as film production and virtual reality, yet deploying its computationally intensive models on resource-constrained devices presents c…
Event-Priori-Based Vision-Language Model for Efficient Visual Understanding
Haotong Qin, Cheng Hu, Michele Magno
Large Language Model (LLM)-based Vision-Language Models (VLMs) have substantially extended the boundaries of visual understanding capabilities. However, their high computational de…
PicoSAM2: Low-Latency Segmentation In-Sensor for Edge Vision Applications
Pietro Bonazzi, Nicola Farronato, Stefan Zihlmann +2
Real-time, on-device segmentation is critical for latency-sensitive and privacy-aware applications like smart glasses and IoT devices. We introduce PicoSAM2, a lightweight (1.3M pa…