Publications (33)
On the Power-Law Hessian Spectrums in Deep Learning
Zeke Xie, Qian-Yuan Tang, Yunfeng Cai +2
It is well-known that the Hessian of deep loss landscape matters to optimization, generalization, and even robustness of deep learning. Recent works empirically discovered that the…
Actively Supervised Clustering for Open Relation Extraction
Jun Zhao, Yongxin Zhang, Qi Zhang +4
Current clustering-based Open Relation Extraction (OpenRE) methods usually adopt a two-stage pipeline. The first stage simultaneously learns relation representations and assignment…
NL2GDPR: Automatically Develop GDPR Compliant Android Application Features from Natural Language
Faysal Hossain Shezan, Yingjie Lao, Minlong Peng +3
The recent privacy leakage incidences and the more strict policy regulations demand a much higher standard of compliance for companies and mobile apps. However, such obligations al…
Joint learning of object graph and relation graph for visual question answering
Hao Li, Xu Li, Belhal Karimi +2
Modeling visual question answering(VQA) through scene graphs can significantly improve the reasoning accuracy and interpretability. However, existing models answer poorly for compl…
RE-Matching: A Fine-Grained Semantic Matching Method for Zero-Shot Relation Extraction
Jun Zhao, Wenyu Zhan, Xin Zhao +6
Semantic matching is a mainstream paradigm of zero-shot relation extraction, which matches a given input with a corresponding label description. The entities in the input should ex…
S3IM: Stochastic Structural SIMilarity and Its Unreasonable Effectiveness for Neural Fields
Zeke Xie, Xindi Yang, Yujie Yang +5
Recently, Neural Radiance Field (NeRF) has shown great success in rendering novel-view images of a given scene by learning an implicit representation with only posed RGB images. Ne…
A Semi-Autoregressive Graph Generative Model for Dependency Graph Parsing
Ye Ma, Mingming Sun, Ping Li
Recent years have witnessed the impressive progress in Neural Dependency Parsing. According to the different factorization approaches to the graph joint probabilities, existing par…
CGAR: Critic Guided Action Redistribution in Reinforcement Leaning
Tairan Huang, Xu Li, Hao Li +2
Training a game-playing reinforcement learning agent requires multiple interactions with the environment. Ignorant random exploration may cause a waste of time and resources. It's…
Large Margin Prototypical Network for Few-shot Relation Classification with Fine-grained Features
Miao Fan, Yeqi Bai, Mingming Sun +1
Relation classification (RC) plays a pivotal role in both natural language understanding and knowledge graph completion. It is generally formulated as a task to recognize the relat…
Semantic Distance Measurement based on Multi-Kernel Gaussian Processes
Yinzhu Cheng, Haihua Xie, Yaqing Wang +2
Semantic distance measurement is a fundamental problem in computational linguistics, providing a quantitative characterization of similarity or relatedness between text segments, a…
Unlocking New Paths for Science with Extreme-Mass-Ratio Inspirals: Machine Learning-Enhanced MCMC for Accurate Parameter Inversion
Bo Liang, Chang Liu, Hanlin Song +11
The detection of gravitational waves from extreme-mass-ratio inspirals (EMRIs) in space-borne antennas like Taiji and LISA promises deep insights into strong-field gravity and blac…
Learning from Ambiguous Data with Hard Labels
Zeke Xie, Zheng He, Nan Lu +5
Real-world data often contains intrinsic ambiguity that the common single-hard-label annotation paradigm ignores. Standard training using ambiguous data with these hard labels may…
Dataset Pruning: Reducing Training Data by Examining Generalization Influence
Shuo Yang, Zeke Xie, Hanyu Peng +3
The great success of deep learning heavily relies on increasingly larger training data, which comes at a price of huge computational and infrastructural costs. This poses crucial q…
DocTER: Evaluating Document-based Knowledge Editing
Suhang Wu, Ante Wang, Minlong Peng +4
Knowledge editing aims to correct outdated or inaccurate knowledge in neural networks. In this paper, we explore knowledge editing using easily accessible documents instead of manu…
Under-confidence Backdoors Are Resilient and Stealthy Backdoors
Minlong Peng, Zidi Xiong, Quang H. Nguyen +3
By injecting a small number of poisoned samples into the training set, backdoor attacks aim to make the victim model produce designed outputs on any input injected with pre-designe…
A Graph-Guided Reasoning Approach for Open-ended Commonsense Question Answering
Zhen Han, Yue Feng, Mingming Sun
Recently, end-to-end trained models for multiple-choice commonsense question answering (QA) have delivered promising results. However, such question-answering systems cannot be dir…
Logician: A Unified End-to-End Neural Approach for Open-Domain Information Extraction
Mingming Sun, Xu Li, Xin Wang +3
In this paper, we consider the problem of open information extraction (OIE) for extracting entity and relation level intermediate structures from sentences in open-domain. We focus…
FluxMC: Rapid and High-Fidelity Inference for Space-Based Gravitational-Wave Observations
Bo Liang, Chang Liu, Hanlin Song +11
Bayesian inference in the physical sciences faces a fundamental challenge: the imperative for high-fidelity physical modeling often clashes with the intrinsic limitations of stocha…
SpaceE: Knowledge Graph Embedding by Relational Linear Transformation in the Entity Space
Jinxing Yu, Yunfeng Cai, Mingming Sun +1
Translation distance based knowledge graph embedding (KGE) methods, such as TransE and RotatE, model the relation in knowledge graphs as translation or rotation in the vector space…
On the Overlooked Structure of Stochastic Gradients
Zeke Xie, Qian-Yuan Tang, Mingming Sun +1
Stochastic gradients closely relate to both optimization and generalization of deep neural networks (DNNs). Some works attempted to explain the success of stochastic optimization f…
S-MLP: Spatial-Shift MLP Architecture for Vision
Tan Yu, Xu Li, Yunfeng Cai +2
Recently, visual Transformer (ViT) and its following works abandon the convolution and exploit the self-attention operation, attaining a comparable or even higher accuracy than CNN…
Tool Graph Retriever: Exploring Dependency Graph-based Tool Retrieval for Large Language Models
Linfeng Gao, Yaoxiang Wang, Minlong Peng +4
With the remarkable advancement of AI agents, the number of their equipped tools is increasing rapidly. However, integrating all tool information into the limited model context bec…
Neural Field Classifiers via Target Encoding and Classification Loss
Xindi Yang, Zeke Xie, Xiong Zhou +6
Neural field methods have seen great progress in various long-standing tasks in computer vision and computer graphics, including novel view synthesis and geometry reconstruction. A…
SGD: Street View Synthesis with Gaussian Splatting and Diffusion Prior
Zhongrui Yu, Haoran Wang, Jinze Yang +6
Novel View Synthesis (NVS) for street scenes play a critical role in the autonomous driving simulation. The current mainstream technique to achieve it is neural rendering, such as…
HiCAST: Highly Customized Arbitrary Style Transfer with Adapter Enhanced Diffusion Models
Hanzhang Wang, Haoran Wang, Jinze Yang +7
The goal of Arbitrary Style Transfer (AST) is injecting the artistic features of a style reference into a given image/video. Existing methods usually focus on pursuing the balance…
MOBIUS: Towards the Next Generation of Query-Ad Matching in Baidu's Sponsored Search
Miao Fan, Jiacheng Guo, Shuai Zhu +3
Baidu runs the largest commercial web search engine in China, serving hundreds of millions of online users every day in response to a great variety of queries. In order to build a…
Distributed Hierarchical GPU Parameter Server for Massive Scale Deep Learning Ads Systems
Weijie Zhao, Deping Xie, Ronglai Jia +4
Neural networks of ads systems usually take input from multiple resources, e.g., query-ad relevance, ad features and user portraits. These inputs are encoded into one-hot or multi-…
VIP: Versatile Image Outpainting Empowered by Multimodal Large Language Model
Jinze Yang, Haoran Wang, Zining Zhu +3
In this paper, we focus on resolving the problem of image outpainting, which aims to extrapolate the surrounding parts given the center contents of an image. Although recent works…
One2set + Large Language Model: Best Partners for Keyphrase Generation
Liangying Shao, Liang Zhang, Minlong Peng +4
Keyphrase generation (KPG) aims to automatically generate a collection of phrases representing the core concepts of a given document. The dominant paradigms in KPG include one2seq…
S-MLPv2: Improved Spatial-Shift MLP Architecture for Vision
Tan Yu, Xu Li, Yunfeng Cai +2
Recently, MLP-based vision backbones emerge. MLP-based vision architectures with less inductive bias achieve competitive performance in image recognition compared with CNNs and vis…
Beyond Static Visual Tokens: Structured Sequential Visual Chain-of-Thought Reasoning
Guangfu Guo, Xiaoqian Lu, Yue Feng +1
Current multimodal LLMs encode images as static visual prefixes and rely on text-based reasoning, lacking goal-driven and adaptive visual access. Inspired by human visual perceptio…
MQuinE: a cure for "Z-paradox" in knowledge graph embedding models
Yang Liu, Huang Fang, Yunfeng Cai +1
Knowledge graph embedding (KGE) models achieved state-of-the-art results on many knowledge graph tasks including link prediction and information retrieval. Despite the superior per…
Rethinking Token-Mixing MLP for MLP-based Vision Backbone
Tan Yu, Xu Li, Yunfeng Cai +2
In the past decade, we have witnessed rapid progress in the machine vision backbone. By introducing the inductive bias from the image processing, convolution neural network (CNN) h…