no code implementations • 3 Apr 2025 • Weibin Liao, Xin Gao, Tianyu Jia, Rihong Qiu, Yifan Zhu, Yang Lin, Xu Chu, Junfeng Zhao, Yasha Wang
Inspired by the application of reinforcement learning in mathematical problem-solving to encourage step-by-step reasoning in LLMs, we propose LearNAT (Learning NL2SQL with AST-guided Task Decomposition), a novel framework that improves the performance of open-source LLMs on complex NL2SQL tasks through task decomposition and reinforcement learning.
1 code implementation • 27 Mar 2025 • Haoran Luo, Haihong E, Guanting Chen, Yandan Zheng, Xiaobao Wu, Yikai Guo, Qika Lin, Yu Feng, Zemin Kuang, Meina Song, Yifan Zhu, Luu Anh Tuan
To retrieve and generate over hypergraphs, we introduce a complete pipeline with a hypergraph construction method, a hypergraph retrieval strategy, and a hypergraph-guided generation mechanism.
no code implementations • 12 Mar 2025 • Hannah VanderHoeven, Brady Bhalla, Ibrahim Khebour, Austin Youngren, Videep Venkatesha, Mariah Bradford, Jack FitzGerald, Carlos Mabrey, Jingxuan Tu, Yifan Zhu, Kenneth Lai, Changsoo Jung, James Pustejovsky, Nikhil Krishnaswamy
We present TRACE, a novel system for live *common ground* tracking in situated collaborative tasks.
no code implementations • 6 Mar 2025 • Lijia Yu, Yibo Miao, Yifan Zhu, Xiao-Shan Gao, Lijun Zhang
Classic uniform generalization bounds, which rely on VC-dimension or Rademacher complexity, fail to explain the significant attribute that over-parameterized models in deep learning exhibit nice generalizability.
1 code implementation • 6 Mar 2025 • Shuang Liu, Yihan Wang, Yifan Zhu, Yibo Miao, Xiao-Shan Gao
Wasserstein distributionally robust optimization (WDRO) optimizes against worst-case distributional shifts within a specified uncertainty set, leading to enhanced generalization on unseen adversarial examples, compared to standard adversarial training which focuses on pointwise adversarial perturbations.
1 code implementation • 20 Feb 2025 • Mengyang Sun, Yihao Wang, Tao Feng, Dan Zhang, Yifan Zhu, Jie Tang
In order to streamline the fine-tuning of foundation models, Low-Rank Adapters (LoRAs) have been substantially adopted across various fields, including instruction tuning and domain adaptation.
1 code implementation • 17 Feb 2025 • Shuai Lyu, Haoran Luo, Zhonghong Ou, Yifan Zhu, Xiaoran Shang, Yang Qin, Meina Song
To address these issues, we propose SQL-o1, a Self-Reward-based heuristic search method designed to enhance the reasoning ability of LLMs in SQL query generation.
1 code implementation • 15 Feb 2025 • Insu Han, Zeliang Zhang, Zhiyuan Wang, Yifan Zhu, Susan Liang, Jiani Liu, Haiting Lin, Mingjie Zhao, Chenliang Xu, Kun Wan, Wentian Zhao
While Key-Value (KV) caching effectively trades memory for computation to enhance inference efficiency, the growing memory footprint from extensive KV caches significantly reduces throughput and restricts prolonged deployment on memory-constrained GPU devices.
1 code implementation • 1 Feb 2025 • Yu Feng, Yangli-ao Geng, Yifan Zhu, Zongfu Han, Xie Yu, Kaiwen Xue, Haoran Luo, Mengyang Sun, Guangwei Zhang, Meina Song
Federated learning (FL) has gained widespread attention for its privacy-preserving and collaborative learning capabilities.
1 code implementation • 31 Jan 2025 • Haoran Luo, Haihong E, Yikai Guo, Qika Lin, Xiaobao Wu, Xinyu Mu, Wenhao Liu, Meina Song, Yifan Zhu, Luu Anh Tuan
Moreover, it employs MCTS, a heuristic search method driven by policy and reward models, to balance agentic exploration's performance and search space.
no code implementations • 19 Jan 2025 • Shuai Lyu, Zijing Tian, Zhonghong Ou, Yifan Zhu, Xiao Zhang, Qiankun Ha, Haoran Luo, Meina Song
In order to resolve this problem, we introduce a Tripartite learning with Semantic Variation Consistency (TSVC) for robust image-text retrieval.
1 code implementation • 18 Dec 2024 • Ruichen Qiu, Yibo Miao, Shiwen Wang, Lijia Yu, Yifan Zhu, Xiao-Shan Gao
The Kolmogorov-Arnold Network (KAN) is a new network architecture known for its high accuracy in several tasks such as function fitting and PDE solving.
no code implementations • 8 Dec 2024 • Derek Palmer, Yifan Zhu, Kenneth Lai, Hannah VanderHoeven, Mariah Bradford, Ibrahim Khebour, Carlos Mabrey, Jack FitzGerald, Nikhil Krishnaswamy, Martha Palmer, James Pustejovsky
Our goal is to develop an AI Partner that can provide support for group problem solving and social dynamics.
no code implementations • 29 Nov 2024 • Yifan Zhu, Tianyi Xiang, Aaron Dollar, Zherong Pan
Identifying predictive world models for robots in novel environments from sparse online observations is essential for robot task planning and execution in novel environments.
no code implementations • 15 Oct 2024 • Guangxin Su, Yifan Zhu, Wenjie Zhang, Hanchen Wang, Ying Zhang
In this paper, we introduce LangGSL, a robust framework that integrates the complementary strengths of pre-trained language models and GSLMs to jointly enhance both node feature and graph structure learning.
1 code implementation • 23 Aug 2024 • Qika Lin, Yifan Zhu, Xin Mei, Ling Huang, Jingying Ma, Kai He, Zhen Peng, Erik Cambria, Mengling Feng
The rapid development of artificial intelligence has constantly reshaped the field of intelligent healthcare and medicine.
no code implementations • 6 Aug 2024 • Yifan Zhu, Pranay Thangeda, Erica L Tevere, Ashish Goel, Erik Kramer, Hari D Nayar, Melkior Ornik, Kris Hauser
Our Deep Kernel Calibration with Maximal Deployment Gaps (kCMD) strategy explicitly trains a deep kernel model to adapt to large domain shifts by creating simulated maximal deployment gaps from an offline training dataset and training models to overcome these deployment gaps during training.
no code implementations • 30 Jul 2024 • Weibin Liao, Yifan Zhu, Yanyan Li, Qi Zhang, Zhonghong Ou, Xuesong Li
Therefore, investigating how to better comprehend the negative labeling of unobserved interactions in academic reviewer recommendations is a significant challenge.
1 code implementation • 22 Jul 2024 • Yu Feng, Zhen Tian, Yifan Zhu, Zongfu Han, Haoran Luo, Guangwei Zhang, Meina Song
The key challenge of cross-modal domain-incremental learning (DIL) is to enable the learning model to continuously learn from novel data with different feature distributions under the same task without forgetting old ones.
no code implementations • 8 Jul 2024 • Yibo Miao, Yifan Zhu, Yinpeng Dong, Lijia Yu, Jun Zhu, Xiao-Shan Gao
The recent development of Sora leads to a new era in text-to-video (T2V) generation.
1 code implementation • 26 Mar 2024 • Ibrahim Khebour, Kenneth Lai, Mariah Bradford, Yifan Zhu, Richard Brutti, Christopher Tam, Jingxuan Tu, Benjamin Ibarra, Nathaniel Blanchard, Nikhil Krishnaswamy, James Pustejovsky
Within Dialogue Modeling research in AI and NLP, considerable attention has been spent on ``dialogue state tracking'' (DST), which is the ability to update the representations of the speaker's needs at each turn in the dialogue by taking into account the past dialogue moves and history.
1 code implementation • 24 Feb 2024 • Fanjin Zhang, Shijie Shi, Yifan Zhu, Bo Chen, Yukuo Cen, Jifan Yu, Yelin Chen, Lulu Wang, Qingfei Zhao, Yuqing Cheng, Tianyi Han, Yuwei An, Dan Zhang, Weng Lam Tam, Kun Cao, Yunhe Pang, Xinyu Guan, Huihui Yuan, Jian Song, Xiaoyan Li, Yuxiao Dong, Jie Tang
We envisage that OAG-Bench can serve as a common ground for the community to evaluate and compare algorithms in academic graph mining, thereby accelerating algorithm development and advancement in this field.
no code implementations • 10 Feb 2024 • Yifan Zhu, Lingjuan Miao, Haitao Wu, Zhiqiang Zhou, Weiyi Chen, Longwen Wu
Due to the improvement of CNN-based object detection algorithm, the robustness of visual relocalization is greatly enhanced especially in viewpoints where classical methods fail.
no code implementations • 6 Feb 2024 • Yihan Wang, Yifan Zhu, Xiao-Shan Gao
Availability attacks can prevent the unauthorized use of private data and commercial datasets by generating imperceptible noise and making unlearnable examples before release.
1 code implementation • 14 Dec 2023 • Yifan Zhu, Lijia Yu, Xiao-Shan Gao
Detectability of unlearnable examples with simple networks motivates us to design a novel defense method.
no code implementations • 28 Nov 2023 • Jiaqi Ruan, Xiangrui Meng, Yifan Zhu, Gaoqi Liang, Xianzhuo Sun, Huayi Wu, Huijuan Xiao, Mengqian Lu, Pin Gao, Jiapeng Li, Wai-kin Wong, Zhao Xu, Junhua Zhao
Modern society's reliance on power systems is at risk from the escalating effects of wind-related climate change.
no code implementations • 22 Nov 2023 • Zeliang Zhang, Zhuo Liu, Susan Liang, Zhiyuan Wang, Yifan Zhu, Chen Ding, Chenliang Xu
However, the application of tensor decomposition is largely hindered by the exponential increment of the computational complexity and storage consumption with the size of tensors.
1 code implementation • 13 Oct 2023 • Haoran Luo, Haihong E, Zichen Tang, Shiyao Peng, Yikai Guo, Wentai Zhang, Chenghao Ma, Guanting Dong, Meina Song, Wei Lin, Yifan Zhu, Luu Anh Tuan
Knowledge Base Question Answering (KBQA) aims to answer natural language questions over large-scale knowledge bases (KBs), which can be summarized into two crucial steps: knowledge retrieval and semantic parsing.
Ranked #1 on
Knowledge Base Question Answering
on WebQuestionsSP
1 code implementation • 8 Oct 2023 • Haoran Luo, Haihong E, Yuhao Yang, Tianyu Yao, Yikai Guo, Zichen Tang, Wentai Zhang, Kaiyang Wan, Shiyao Peng, Meina Song, Wei Lin, Yifan Zhu, Luu Anh Tuan
However, the construction of NKGs remains at a coarse-grained level, which is always in a single schema, ignoring the order and variable arity of entities.
Event-based N-ary Relaiton Extraction
Hypergraph-based N-ary Relaiton Extraction
+3
1 code implementation • ICCV 2023 • Fei Gao, Yifan Zhu, Chang Jiang, Nannan Wang
Besides, different artists may use diverse drawing techniques and create multiple styles of sketches; but the style is globally consistent in a sketch.
no code implementations • 10 Jul 2023 • Saurabh Kumar, Henrik Marklund, Ashish Rao, Yifan Zhu, Hong Jun Jeon, Yueyang Liu, Benjamin Van Roy
The design of such agents, which remains a long-standing challenge of artificial intelligence, is addressed by the subject of continual learning.
1 code implementation • CVPR 2023 • Jiaxiong Qiu, Peng-Tao Jiang, Yifan Zhu, Ze-Xin Yin, Ming-Ming Cheng, Bo Ren
To remedy this issue, we present a novel surface reconstruction framework, NeuS-HSR, based on implicit neural rendering.
no code implementations • ICCV 2023 • Yuxiang Cai, Yifan Zhu, Haiwei Zhang, Bo Ren
We compare the metrics on our dataset and SLAM reconstruction results in both synthetic scenes and real scenes with the previous methods.
no code implementations • 18 Sep 2022 • Yifan Zhu, Hong Jun Jeon, Benjamin Van Roy
However, existing computational theory suggests that, even for single-hidden-layer teacher networks, to attain small error for all such teacher networks, the computation required to achieve this sample complexity is intractable.
no code implementations • 6 Sep 2022 • Jia Zheng, Yifan Zhu, Kehan Wang, Qiang Zou, Zihan Zhou
In this paper, we revisit the long-standing problem of automatic reconstruction of 3D objects from single line drawings.
no code implementations • 15 Aug 2022 • Zepeng Huai, Zhe Wang, Yifan Zhu, Peng Zhang
Paper recommendation with user-generated keyword is to suggest papers that simultaneously meet user's interests and are relevant to the input keyword.
no code implementations • 1 Mar 2022 • Hong Jun Jeon, Yifan Zhu, Benjamin Van Roy
For a particular prior distribution on weights, we establish sample complexity bounds that are simultaneously width independent and linear in depth.
no code implementations • 27 Oct 2021 • Huayan Guo, Yifan Zhu, Haoyu Ma, Vincent K. N. Lau, Kaibin Huang, Xiaofan Li, Huabin Nong, Mingyu Zhou
In this paper, we develop an orthogonal-frequency-division-multiplexing (OFDM)-based over-the-air (OTA) aggregation solution for wireless federated learning (FL).
no code implementations • 19 Oct 2021 • Yifan Zhu, Fan Dai, Ranjan Maitra
We develop methodology for three-dimensional (3D) radial visualization (RadViz) of multidimensional datasets.
no code implementations • 16 Oct 2021 • Gen Shi, Yifan Zhu, Wenjin Liu, Quanming Yao, Xuesong Li
Other experiments also indicate that our proposed model with a pretraining strategy alleviates the problem of limited labelled data and yields a significant improvement in accuracy.
no code implementations • 7 Jan 2021 • Yifan Zhu, Nikhil JRK Gerard, Xiaoxing Xia, Grant C. Stevenson, Liyun Cao, Shiwang Fan, Christopher M. Spadaccini, Yun Jing, Badreddine Assouar
Acoustic holograms have promising applications in sound-field reconstruction, particle manipulation, ultrasonic haptics and therapy.
Applied Physics
no code implementations • ICCV 2021 • Yifan Zhu, Jiaxiong Qiu, Bo Ren
In this paper, we propose a novel SLAM approach called transfusion that allows transparent object existence and recovery in the video input.
no code implementations • 4 Mar 2020 • Fanyi Xiao, Ling Pei, Lei Chu, Danping Zou, Wenxian Yu, Yifan Zhu, Tao Li
The experimental results show that the proposed method can surprisingly converge in a few iterations and achieve an accuracy of 91. 15% on a real IMU dataset, demonstrating the efficiency and effectiveness of the proposed method.
no code implementations • 6 Apr 2019 • Yifan Zhu, Fan Dai, Ranjan Maitra
We develop methodology for visualization of labeled mixed-featured datasets.