no code implementations • 31 Jan 2025 • Ying Wen, Ziyu Wan, Shao Zhang
The evolution of large language models (LLMs) toward artificial superhuman intelligence (ASI) hinges on data reproduction, a cyclical process in which models generate, curate and retrain on novel data to refine capabilities.
1 code implementation • 21 Nov 2024 • Xidong Feng, Ziyu Wan, Haotian Fu, Bo Liu, Mengyue Yang, Girish A. Koushik, Zhiyuan Hu, Ying Wen, Jun Wang
Reinforcement Learning (RL) mathematically formulates decision-making with Markov Decision Process (MDP).
1 code implementation • 12 Oct 2024 • Jun Wang, Meng Fang, Ziyu Wan, Muning Wen, Jiachen Zhu, Anjie Liu, Ziqin Gong, Yan Song, Lei Chen, Lionel M. Ni, Linyi Yang, Ying Wen, Weinan Zhang
Inspired by the success of OpenAI's o1 model, which demonstrated improved reasoning abilities through step-by-step reasoning and reinforcement learning, OpenR integrates test-time compute, reinforcement learning, and process supervision to improve reasoning in LLMs.
no code implementations • 5 Oct 2024 • Long Zhao, Sanghyun Woo, Ziyu Wan, Yandong Li, Han Zhang, Boqing Gong, Hartwig Adam, Xuhui Jia, Ting Liu
Current visual tokenization methods rely on a traditional autoencoder framework, where the encoder compresses data into latent representations, and the decoder reconstructs the original input.
no code implementations • 6 Aug 2024 • Xingguang Yan, Han-Hung Lee, Ziyu Wan, Angel X. Chang
We introduce a new approach for generating realistic 3D models with UV maps through a representation termed "Object Images."
1 code implementation • 28 May 2024 • Qi Sun, Zhiyang Guo, Ziyu Wan, Jing Nathan Yan, Shengming Yin, Wengang Zhou, Jing Liao, Houqiang Li
In recent years, the increasing demand for dynamic 3D assets in design and gaming applications has given rise to powerful generative pipelines capable of synthesizing high-quality 4D objects.
no code implementations • 4 Apr 2024 • Zhongkai Wu, Ziyu Wan, Jing Zhang, Jing Liao, Dong Xu
Instead of reconstructing a blurred NeRF by averaging inconsistencies, we introduce a novel approach using Generative Adversarial Networks (GANs) for NeRF generation to better accommodate the geometric and appearance inconsistencies present in the multi-view images.
no code implementations • 11 Feb 2024 • Xidong Feng, Ziyu Wan, Mengyue Yang, Ziyan Wang, Girish A. Koushik, Yali Du, Ying Wen, Jun Wang
Reinforcement Learning (RL) has shown remarkable abilities in learning policies for decision-making tasks.
no code implementations • 12 Dec 2023 • Hongyu Liu, Xuan Wang, Ziyu Wan, Yujun Shen, Yibing Song, Jing Liao, Qifeng Chen
The noisy image, landmarks, and text condition are then fed into the frozen ControlNet twice for noise prediction.
no code implementations • CVPR 2024 • Ziyu Wan, Despoina Paschalidou, IAn Huang, Hongyu Liu, Bokui Shen, Xiaoyu Xiang, Jing Liao, Leonidas Guibas
The increased demand for 3D data in AR/VR, robotics and gaming applications, gave rise to powerful generative pipelines capable of synthesizing high-quality 3D objects.
1 code implementation • 29 Sep 2023 • Xidong Feng, Ziyu Wan, Muning Wen, Stephen Marcus McAleer, Ying Wen, Weinan Zhang, Jun Wang
Empirical results across reasoning, planning, alignment, and decision-making tasks show that TS-LLM outperforms existing approaches and can handle trees with a depth of 64.
1 code implementation • 19 May 2023 • Jingbo Zhang, Xiaoyu Li, Ziyu Wan, Can Wang, Jing Liao
Extensive experiments demonstrate that our Text2NeRF outperforms existing methods in producing photo-realistic, multi-view consistent, and diverse 3D scenes from a variety of natural language prompts.
no code implementations • CVPR 2023 • Ziyu Wan, Christian Richardt, Aljaž Božič, Chao Li, Vijay Rengarajan, Seonghyeon Nam, Xiaoyu Xiang, Tuotuo Li, Bo Zhu, Rakesh Ranjan, Jing Liao
Neural radiance fields (NeRFs) enable novel view synthesis with unprecedented visual quality.
1 code implementation • 13 Feb 2023 • Xihuai Wang, Zheng Tian, Ziyu Wan, Ying Wen, Jun Wang, Weinan Zhang
In this paper, we propose the \textbf{A}gent-by-\textbf{a}gent \textbf{P}olicy \textbf{O}ptimization (A2PO) algorithm to improve the sample efficiency and retain the guarantees of monotonic improvement for each agent during training.
1 code implementation • 24 Dec 2022 • Ying Wen, Ziyu Wan, Ming Zhou, Shufang Hou, Zhe Cao, Chenyang Le, Jingxiao Chen, Zheng Tian, Weinan Zhang, Jun Wang
The pervasive uncertainty and dynamic nature of real-world environments present significant challenges for the widespread implementation of machine-driven Intelligent Decision-Making (IDM) systems.
no code implementations • 15 Aug 2022 • Jingbo Zhang, Ziyu Wan, Jing Liao
Due to inevitable noises introduced during scanning and quantization, 3D reconstruction via RGB-D sensors suffers from errors both in geometry and texture, leading to artifacts such as camera drifting, mesh distortion, texture ghosting, and blurriness.
1 code implementation • 11 Aug 2022 • Jingbo Zhang, Xiaoyu Li, Ziyu Wan, Can Wang, Jing Liao
Unlike existing dynamic NeRFs that require dense images as input and can only be modeled for a single identity, our method enables face reconstruction across different persons with few-shot inputs.
1 code implementation • CVPR 2022 • Ziyu Wan, Bo Zhang, Dongdong Chen, Jing Liao
We present a learning-based framework, recurrent transformer network (RTN), to restore heavily degraded old films.
Ranked #6 on
Analog Video Restoration
on TAPE
1 code implementation • NeurIPS 2021 • Xidong Feng, Oliver Slumbers, Ziyu Wan, Bo Liu, Stephen Mcaleer, Ying Wen, Jun Wang, Yaodong Yang
When solving two-player zero-sum games, multi-agent reinforcement learning (MARL) algorithms often create populations of agents where, at each iteration, a new agent is discovered as the best response to a mixture over the opponent population.
Multi-agent Reinforcement Learning
Vocal Bursts Valence Prediction
1 code implementation • 5 Jun 2021 • Ming Zhou, Ziyu Wan, Hanjing Wang, Muning Wen, Runzhe Wu, Ying Wen, Yaodong Yang, Weinan Zhang, Jun Wang
Our framework is comprised of three key components: (1) a centralized task dispatching model, which supports the self-generated tasks and scalable training with heterogeneous policy combinations; (2) a programming architecture named Actor-Evaluator-Learner, which achieves high parallelism for both training and sampling, and meets the evaluation requirement of auto-curriculum learning; (3) a higher-level abstraction of MARL training paradigms, which enables efficient code reuse and flexible deployments on different distributed computing paradigms.
1 code implementation • 4 Jun 2021 • Xidong Feng, Oliver Slumbers, Ziyu Wan, Bo Liu, Stephen Mcaleer, Ying Wen, Jun Wang, Yaodong Yang
When solving two-player zero-sum games, multi-agent reinforcement learning (MARL) algorithms often create populations of agents where, at each iteration, a new agent is discovered as the best response to a mixture over the opponent population.
1 code implementation • CVPR 2021 • Hongyu Liu, Ziyu Wan, Wei Huang, Yibing Song, Xintong Han, Jing Liao
To this end, we propose spatially probabilistic diversity normalization (SPDNorm) inside the modulation to model the probability of generating a pixel conditioned on the context information.
4 code implementations • ICCV 2021 • Ziyu Wan, Jingbo Zhang, Dongdong Chen, Jing Liao
Image completion has made tremendous progress with convolutional neural networks (CNNs), because of their powerful texture modeling capacity.
Ranked #7 on
Image Inpainting
on CelebA-HQ
1 code implementation • CVPR 2021 • Hongyu Liu, Ziyu Wan, Wei Huang, Yibing Song, Xintong Han, Jing Liao, Bing Jiang, Wei Liu
While existing methods combine an input image and these low-level controls for CNN inputs, the corresponding feature representations are not sufficient to convey user intentions, leading to unfaithfully generated content.
1 code implementation • 8 Feb 2021 • Shuquan Ye, Dongdong Chen, Songfang Han, Ziyu Wan, Jing Liao
Thus, Meta-PU even outperforms the existing methods trained for a specific scale factor only.
Graphics