no code implementations • 17 Dec 2024 • Yiping Wang, Xuehai He, Kuan Wang, Luyao Ma, Jianwei Yang, Shuohang Wang, Simon Shaolei Du, Yelong Shen
However, they still struggle to coherently present multiple sequential events in the stories specified by the prompts, which is foreseeable an essential capability for future long video generation scenarios.
no code implementations • 12 Dec 2024 • Xuehai He, Shuohang Wang, Jianwei Yang, Xiaoxia Wu, Yiping Wang, Kuan Wang, Zheng Zhan, Olatunji Ruwase, Yelong Shen, Xin Eric Wang
Recent advancements in diffusion models have shown great promise in producing high-quality video content.
no code implementations • 10 Sep 2024 • Kuan Wang, Alexander Bukharin, Haoming Jiang, Qingyu Yin, Zhengyang Wang, Tuo Zhao, Jingbo Shang, Chao Zhang, Bing Yin, Xian Li, Jianshu Chen, Shiyang Li
However, existing models trained on open-source IFT datasets only have the ability to follow instructions from users, and often fail to follow complex role and rules specified by developers, a. k. a.
no code implementations • 21 Feb 2024 • Lingxi Zhang, Yue Yu, Kuan Wang, Chao Zhang
Retrieval-augmented generation enhances large language models (LLMs) by incorporating relevant information from external knowledge sources.
no code implementations • 1 Oct 2023 • Kuan Wang, Yadong Lu, Michael Santacroce, Yeyun Gong, Chao Zhang, Yelong Shen
To optimize agent interactions for task-specific learning with our universal buffer and pipeline, we introduce diverse communication patterns tailored for both single-agent and multi-agent environments.
2 code implementations • NeurIPS 2023 • Yuchen Zhuang, Yue Yu, Kuan Wang, Haotian Sun, Chao Zhang
To address this issue, we introduce a new dataset called ToolQA, which is designed to faithfully evaluate LLMs' ability to use external tools for question answering.
no code implementations • 20 Dec 2022 • Dong Li, Yelong Shen, Ruoming Jin, Yi Mao, Kuan Wang, Weizhu Chen
Pre-trained language models have achieved promising success in code retrieval tasks, where a natural language documentation query is given to find the most relevant existing code snippet.
no code implementations • ICLR 2022 • Kuan Wang, Yuyu Zhang, Diyi Yang, Le Song, Tao Qin
To open the black box of GNN and investigate these problems, we dissect state-of-the-art GNN modules for QA and analyze their reasoning capability.
Ranked #12 on
Question Answering
on OpenBookQA
4 code implementations • 27 Sep 2021 • Ji Lin, Chuang Gan, Kuan Wang, Song Han
Secondly, TSM has high efficiency; it achieves a high frame rate of 74fps and 29fps for online video recognition on Jetson Nano and Galaxy Note8.
no code implementations • 22 Mar 2021 • Karan Samel, Zelin Zhao, Binghong Chen, Kuan Wang, Robin Luo, Le Song
In multi-modal reasoning tasks, such as visual question answering (VQA), there have been many modeling and training paradigms tested.
no code implementations • 1 Jan 2021 • Karan Samel, Zelin Zhao, Kuan Wang, Robin Luo, Binghong Chen, Le Song
We present a differentiable end-to-end program executor (DePe), which addresses Visual Question Answering (VQA) in a sample and computationally efficient manner.
no code implementations • 11 Aug 2020 • Kuan Wang, Zhijian Liu, Yujun Lin, Ji Lin, Song Han
Compared with conventional methods, our framework is fully automated and can specialize the quantization policy for different neural network architectures and hardware architectures.
1 code implementation • CVPR 2020 • Tianzhe Wang, Kuan Wang, Han Cai, Ji Lin, Zhijian Liu, Song Han
However, training this quantization-aware accuracy predictor requires collecting a large number of quantized <model, accuracy> pairs, which involves quantization-aware finetuning and thus is highly time-consuming.
no code implementations • 30 Apr 2020 • Hanrui Wang, Kuan Wang, Jiacheng Yang, Linxiao Shen, Nan Sun, Hae-Seung Lee, Song Han
Our transferable optimization method makes transistor sizing and design porting more effective and efficient.
no code implementations • 24 Apr 2019 • Song Han, Han Cai, Ligeng Zhu, Ji Lin, Kuan Wang, Zhijian Liu, Yujun Lin
Moreover, we shorten the design cycle by 200x than previous work, so that we can afford to design specialized neural network models for different hardware platforms.
11 code implementations • CVPR 2019 • Kuan Wang, Zhijian Liu, Yujun Lin, Ji Lin, Song Han
Compared with conventional methods, our framework is fully automated and can specialize the quantization policy for different neural network architectures and hardware architectures.
no code implementations • 27 Sep 2018 • Kuan Wang, Hao Zhao, Anbang Yao, Aojun Zhou, Dawei Sun, Yurong Chen
During the training phase, we generate binary weights on-the-fly since what we actually maintain is the policy network, and all the binary weights are used in a burn-after-reading style.
no code implementations • CVPR 2018 • Aojun Zhou, Anbang Yao, Kuan Wang, Yurong Chen
Through explicitly regularizing the loss perturbation and the weight approximation error in an incremental way, we show that such a new optimization method is theoretically reasonable and practically effective.