103 citations · 278 across the 43 of their papers we have counts for
17 papers · 1 filter
Structured Residual Connectivity Matters for Diffusion Transformers
Yuhe Liu, Xinyin Ma, Gongfan Fang +2
Diffusion Transformers (DiTs) have established themselves as a scalable backbone for high-fidelity image synthesis. However, unlike U-Net based diffusion models that rely on rigid,…
Q-ARVD: Quantizing Autoregressive Video Diffusion Models
Siao Tang, Xinyin Ma, Gongfan Fang +2
Autoregressive video diffusion models (ARVDs) have emerged as a promising architecture for streaming video generation, paving the way for real-time interactive video generation and…
Rethinking Token Reduction for Large Vision-Language Models
Yi Wang, Haofei Zhang, Qihan Huang +7
Large Vision-Language Models (LVLMs) excel in visual understanding and reasoning, but the excessive visual tokens lead to high inference costs. Although recent token reduction meth…
In-Video Instructions: Visual Signals as Generative Control
Gongfan Fang, Xinyin Ma, Xinchao Wang
Large-scale video generative models have recently demonstrated strong visual capabilities, enabling the prediction of future frames that adhere to the logical and physical cues in…
Diversity-Guided MLP Reduction for Efficient Large Vision Transformers
Chengchao Shen, Hourun Zhu, Gongfan Fang +2
Transformer models achieve excellent scaling property, where the performance is improved with the increment of model capacity. However, large-scale model parameters lead to an unaf…
PixelThink: Towards Efficient Chain-of-Pixel Reasoning
Song Wang, Gongfan Fang, Lingdong Kong +6
Existing reasoning segmentation approaches typically fine-tune multimodal large language models (MLLMs) using image-text pairs and corresponding mask labels. However, they exhibit…
PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learning
Song Wang, Xiaolu Liu, Lingdong Kong +6
Self-supervised representation learning for point cloud has demonstrated effectiveness in improving pre-trained model performance across diverse tasks. However, as pre-trained mode…
Remix-DiT: Mixing Diffusion Transformers for Multi-Expert Denoising
Gongfan Fang, Xinyin Ma, Xinchao Wang
Transformer-based diffusion models have achieved significant advancements across a variety of generative tasks. However, producing high-quality outputs typically necessitates large…
TinyFusion: Diffusion Transformers Learned Shallow
Gongfan Fang, Kunjun Li, Xinyin Ma +1
Diffusion Transformers have demonstrated remarkable capabilities in image generation but often come with excessive parameterization, resulting in considerable inference overhead in…
Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient
Zigeng Chen, Xinyin Ma, Gongfan Fang +1
In the rapidly advancing field of image generation, Visual Auto-Regressive (VAR) modeling has garnered considerable attention for its innovative next-scale prediction approach. Thi…
Isomorphic Pruning for Vision Models
Gongfan Fang, Xinyin Ma, Michael Bi Mi +1
Structured pruning reduces the computational overhead of deep neural networks by removing redundant sub-structures. However, assessing the relative importance of different sub-stru…
AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising
Zigeng Chen, Xinyin Ma, Gongfan Fang +2
Diffusion models have garnered significant interest from the community for their great generative ability across various applications. However, their typical multi-step sequential-…
DeepCache: Accelerating Diffusion Models for Free
Xinyin Ma, Gongfan Fang, Xinchao Wang
Diffusion models have recently gained unprecedented attention in the field of image synthesis due to their remarkable generative capabilities. Notwithstanding their prowess, these…
SlimSAM: 0.1% Data Makes Segment Anything Slim
Zigeng Chen, Gongfan Fang, Xinyin Ma +1
Current approaches for compressing the Segment Anything Model (SAM) yield commendable results, yet necessitate extensive data to train a new network from scratch. Employing convent…
Federated Selective Aggregation for Knowledge Amalgamation
Donglin Xie, Ruonan Yu, Gongfan Fang +5
In this paper, we explore a new knowledge-amalgamation problem, termed Federated Selective Aggregation (FedSA). The goal of FedSA is to train a student model for a new task with th…
Knowledge Amalgamation for Object Detection with Transformers
Haofei Zhang, Feng Mao, Mengqi Xue +4
Knowledge amalgamation (KA) is a novel deep model reusing task aiming to transfer knowledge from several well-trained teachers to a multi-talented and compact student. Currently, m…
Impression Space from Deep Template Network
Gongfan Fang, Xinchao Wang, Haofei Zhang +2
It is an innate ability for humans to imagine something only according to their impression, without having to memorize all the details of what they have seen. In this work, we woul…