research-papers
Original Paper: https://arxiv.org/abs/2211.10438 By: Guangxuan Xiao, Ji Lin, Mickael Seznec, Hao Wu, Julien Demouth, Song Han Abstract: Large language models (LLMs) show excellent performance but are compute- and memory-intensive. Quantization can reduce memory and accelerate inference. However, existing methods cannot maintain accuracy and hardware efficiency
research-papers
Original Paper: https://arxiv.org/abs/2403.19103 By: Yutong He, Alexander Robey, Naoki Murata, Yiding Jiang, Joshua Williams, George J. Pappas, Hamed Hassani, Yuki Mitsufuji, Ruslan Salakhutdinov, J. Zico Kolter Abstract: Prompt engineering is effective for controlling the output of text-to-image (T2I) generative models, but it is also laborious
research-papers
Original Paper: https://arxiv.org/abs/2310.17569 By: Xinghui Li, Jingyi Lu, Kai Han, Victor Prisacariu Abstract: In this paper, we address the challenge of matching semantically similar keypoints across image pairs. Existing research indicates that the intermediate output of the UNet within the Stable Diffusion (SD) can serve
research-papers
Original Paper: https://arxiv.org/abs/2403.15875 By: Zhicheng Du, Zhaotian Xie, Yan Tong, Peiwu Qin Abstract: This study constructs the LanguAge Model with Prompt EngineeRing (LAMPER) framework, designed to systematically evaluate the adaptability of pre-trained language models (PLMs) in accommodating diverse prompts and their integration in zero-shot time
research-papers
Original Paper: https://arxiv.org/abs/2304.14670 By: Jiaqi Wang, Enze Shi, Sigang Yu, Zihao Wu, Chong Ma, Haixing Dai, Qiushi Yang, Yanqing Kang, Jinru Wu, Huawen Hu, Chenxi Yue, Haiyang Zhang, Yiheng Liu, Yi Pan, Zhengliang Liu, Lichao Sun, Xiang Li, Bao Ge, Xi Jiang, Dajiang Zhu, Yixuan
research-papers
Original Paper: https://arxiv.org/abs/2311.16194 By: Jiawang Bai, Kuofeng Gao, Shaobo Min, Shu-Tao Xia, Zhifeng Li, Wei Liu Abstract: Contrastive Vision-Language Pre-training, known as CLIP, has shown promising effectiveness in addressing downstream image recognition tasks. However, recent works revealed that the CLIP model can be implanted with
research-papers
Original Paper: https://arxiv.org/abs/2312.02918 By: Yuang Ai, Huaibo Huang, Xiaoqiang Zhou, Jiexiang Wang, Ran He Abstract: Despite substantial progress, all-in-one image restoration (IR) grapples with persistent challenges in handling intricate real-world degradations. This paper introduces MPerceiver: a novel multimodal prompt learning approach that harnesses Stable Diffusion
research-papers
Original Paper: https://arxiv.org/abs/2307.01187 By: Haixing Dai, Chong Ma, Zhiling Yan, Zhengliang Liu, Enze Shi, Yiwei Li, Peng Shu, Xiaozheng Wei, Lin Zhao, Zihao Wu, Fang Zeng, Dajiang Zhu, Wei Liu, Quanzheng Li, Lichao Sun, Shu Zhang Tianming Liu, Xiang Li Abstract: This paper introduces SAMAug,
research-papers
Original Paper: https://arxiv.org/abs/2403.11446 By: Clint Morris, Michael Jurado, Jason Zutty Abstract: In the realm of machine learning, traditional model development and automated approaches like AutoML typically rely on layers of abstraction, such as tree-based or Cartesian genetic programming. Our study introduces "Guided Evolution"
research-papers
Original Paper: https://arxiv.org/abs/2312.14091 By: Hayk Manukyan, Andranik Sargsyan, Barsegh Atanyan, Zhangyang Wang, Shant Navasardyan, Humphrey Shi Abstract: Recent progress in text-guided image inpainting, based on the unprecedented success of text-to-image diffusion models, has led to exceptionally realistic and visually plausible results. However, there is still
research-papers
Original Paper: https://arxiv.org/abs/2312.03724 By: Junyuan Hong, Jiachen T. Wang, Chenhui Zhang, Zhangheng Li, Bo Li, Zhangyang Wang Abstract: Large Language Models (LLMs) have emerged as dominant tools for various tasks, particularly when tailored for a specific target by prompt tuning. Nevertheless, concerns surrounding data privacy
research-papers
Original Paper: https://arxiv.org/abs/2310.18961 By: Qihang Zhou, Guansong Pang, Yu Tian, Shibo He, Jiming Chen Abstract: Zero-shot anomaly detection (ZSAD) requires detection models trained using auxiliary data to detect anomalies without any training sample in a target dataset. It is a crucial task when training data