Search Results for author: Yifan Zhu

Found 44 papers, 17 papers with code

LearNAT: Learning NL2SQL with AST-guided Task Decomposition for Large Language Models

no code implementations3 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.

Mathematical Problem-Solving Prompt Engineering +2

HyperGraphRAG: Retrieval-Augmented Generation with Hypergraph-Structured Knowledge Representation

1 code implementation27 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.

RAG Retrieval

Generalizability of Neural Networks Minimizing Empirical Risk Based on Expressive Ability

no code implementations6 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.

Attribute Generalization Bounds

Provable Robust Overfitting Mitigation in Wasserstein Distributionally Robust Optimization

1 code implementation6 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.

A Stronger Mixture of Low-Rank Experts for Fine-Tuning Foundation Models

1 code implementation20 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.

Domain Adaptation

SQL-o1: A Self-Reward Heuristic Dynamic Search Method for Text-to-SQL

1 code implementation17 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.

Few-Shot Learning Natural Language Queries +1

CalibQuant: 1-Bit KV Cache Quantization for Multimodal LLMs

1 code implementation15 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.

Computational Efficiency Quantization

KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search

1 code implementation31 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.

Knowledge Base Question Answering

TSVC:Tripartite Learning with Semantic Variation Consistency for Robust Image-Text Retrieval

no code implementations19 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.

Cross-Modal Retrieval Image-text Retrieval +1

PowerMLP: An Efficient Version of KAN

1 code implementation18 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.

One-Shot Real-to-Sim via End-to-End Differentiable Simulation and Rendering

no code implementations29 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.

Benchmarking Object +1

Bridging Large Language Models and Graph Structure Learning Models for Robust Representation Learning

no code implementations15 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.

Graph Representation Learning Graph structure learning +1

Has Multimodal Learning Delivered Universal Intelligence in Healthcare? A Comprehensive Survey

1 code implementation23 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.

Ethics

Few-shot Scooping Under Domain Shift via Simulated Maximal Deployment Gaps

no code implementations6 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.

Bayesian Optimization Meta-Learning +1

RevGNN: Negative Sampling Enhanced Contrastive Graph Learning for Academic Reviewer Recommendation

no code implementations30 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.

Contrastive Learning Graph Learning

CP-Prompt: Composition-Based Cross-modal Prompting for Domain-Incremental Continual Learning

1 code implementation22 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.

Continual Learning Incremental Learning

Common Ground Tracking in Multimodal Dialogue

1 code implementation26 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.

Dialogue State Tracking

OAG-Bench: A Human-Curated Benchmark for Academic Graph Mining

1 code implementation24 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.

Graph Mining

Semantic Object-level Modeling for Robust Visual Camera Relocalization

no code implementations10 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.

Camera Relocalization Object +3

Efficient Availability Attacks against Supervised and Contrastive Learning Simultaneously

no code implementations6 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.

Contrastive Learning

Detection and Defense of Unlearnable Examples

1 code implementation14 Dec 2023 Yifan Zhu, Lijia Yu, Xiao-Shan Gao

Detectability of unlearnable examples with simple networks motivates us to design a novel defense method.

Adversarial Defense Privacy Preserving

Scalable CP Decomposition for Tensor Learning using GPU Tensor Cores

no code implementations22 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.

Computational Efficiency Tensor Decomposition

ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Models

1 code implementation13 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.

Knowledge Base Question Answering Knowledge Graphs +2

Human-Inspired Facial Sketch Synthesis with Dynamic Adaptation

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.

3D geometry

Continual Learning as Computationally Constrained Reinforcement Learning

no code implementations10 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.

Continual Learning reinforcement-learning +1

Consistent Depth Prediction for Transparent Object Reconstruction from RGB-D Camera

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.

Depth Estimation Depth Prediction +3

Is Stochastic Gradient Descent Near Optimal?

no code implementations18 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.

Deep Learning Assisted Optimization for 3D Reconstruction from Single 2D Line Drawings

no code implementations6 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.

3D Reconstruction

AMinerGNN: Heterogeneous Graph Neural Network for Paper Click-through Rate Prediction with Fusion Query

no code implementations15 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.

Click-Through Rate Prediction Graph Neural Network +1

An Information-Theoretic Framework for Supervised Learning

no code implementations1 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.

Over-the-Air Aggregation for Federated Learning: Waveform Superposition and Prototype Validation

no code implementations27 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).

Federated Learning

Fully Three-dimensional Radial Visualization

no code implementations19 Oct 2021 Yifan Zhu, Fan Dai, Ranjan Maitra

We develop methodology for three-dimensional (3D) radial visualization (RadViz) of multidimensional datasets.

Heterogeneous Graph-Based Multimodal Brain Network Learning

no code implementations16 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.

Disease Prediction Graph Neural Network

Systematic design and experimental demonstration of transmission-type multiplexed acoustic meta-holograms

no code implementations7 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

Transfusion: A Novel SLAM Method Focused on Transparent Objects

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.

Transparent objects

A Deep Learning Method for Complex Human Activity Recognition Using Virtual Wearable Sensors

no code implementations4 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.

Diversity Human Activity Recognition +1

Visualization of Labeled Mixed-featured Datasets

no code implementations6 Apr 2019 Yifan Zhu, Fan Dai, Ranjan Maitra

We develop methodology for visualization of labeled mixed-featured datasets.

Cannot find the paper you are looking for? You can Submit a new open access paper.