4 citations · 9 across the 10 of their papers we have counts for
11 papers
Images Speak Louder Than Scores: Failure Mode Escape for Enhancing Generative Quality
Jie Shao, Ke Zhu, Minghao Fu +2
Diffusion models have achieved remarkable progress in class-to-image generation. However, we observe that despite impressive FID scores, state-of-the-art models often generate dist…
Who Reasons in the Large Language Models?
Jie Shao, Jianxin Wu
Despite the impressive performance of large language models (LLMs), the process of endowing them with new capabilities--such as mathematical reasoning--remains largely empirical an…
All You Need in Knowledge Distillation Is a Tailored Coordinate System
Junjie Zhou, Ke Zhu, Jianxin Wu
Knowledge Distillation (KD) is essential in transferring dark knowledge from a large teacher to a small student network, such that the student can be much more efficient than the t…
Diffusion Product Quantization
Jie Shao, Hanxiao Zhang, Jianxin Wu
In this work, we explore the quantization of diffusion models in extreme compression regimes to reduce model size while maintaining performance. We begin by investigating classical…
Quantization without Tears
Minghao Fu, Hao Yu, Jie Shao +3
Deep neural networks, while achieving remarkable success across diverse tasks, demand significant resources, including computation, GPU memory, bandwidth, storage, and energy. Netw…
Unified Low-rank Compression Framework for Click-through Rate Prediction
Hao Yu, Minghao Fu, Jiandong Ding +2
Deep Click-Through Rate (CTR) prediction models play an important role in modern industrial recommendation scenarios. However, high memory overhead and computational costs limit th…
Minimal Interaction Separated Tuning: A New Paradigm for Visual Adaptation
Ningyuan Tang, Minghao Fu, Jianxin Wu
The rapid scaling of large vision pretrained models makes fine-tuning tasks more and more difficult on devices with low computational resources. We explore a new visual adaptation…
DiffuLT: How to Make Diffusion Model Useful for Long-tail Recognition
Jie Shao, Ke Zhu, Hanxiao Zhang +1
This paper proposes a new pipeline for long-tail (LT) recognition. Instead of re-weighting or re-sampling, we utilize the long-tailed dataset itself to generate a balanced proxy th…
Low-rank Attention Side-Tuning for Parameter-Efficient Fine-Tuning
Ningyuan Tang, Minghao Fu, Ke Zhu +1
In finetuning a large pretrained model to downstream tasks, parameter-efficient fine-tuning (PEFT) methods can effectively finetune pretrained models with few trainable parameters,…
Rectify the Regression Bias in Long-Tailed Object Detection
Ke Zhu, Minghao Fu, Jie Shao +2
Long-tailed object detection faces great challenges because of its extremely imbalanced class distribution. Recent methods mainly focus on the classification bias and its loss func…
DTL: Disentangled Transfer Learning for Visual Recognition
Minghao Fu, Ke Zhu, Jianxin Wu
When pre-trained models become rapidly larger, the cost of fine-tuning on downstream tasks steadily increases, too. To economically fine-tune these models, parameter-efficient tran…