102 citations · 291 across the 22 of their papers we have counts for
22 papers
Kimi K3: Open Frontier Intelligence
Kimi Team, Tongtong Bai, Yifan Bai +398
We introduce Kimi K3, a 2.8T parameter Mixture-of-Experts model with 104 billion activated parameters, native vision capabilities, and a 1-million-token context window. Kimi K3 is…
MatryoshkaThinking: Recursive Test-Time Scaling Enables Efficient Reasoning
Hongwei Chen, Yishu Lei, Dan Zhang +10
Test-time scaling has emerged as a promising paradigm in language modeling, wherein additional computational resources are allocated during inference to enhance model performance.…
HGAMN: Heterogeneous Graph Attention Matching Network for Multilingual POI Retrieval at Baidu Maps
Jizhou Huang, Haifeng Wang, Yibo Sun +4
The increasing interest in international travel has raised the demand of retrieving point of interests in multiple languages. This is even superior to find local venues such as res…
Spectral Heterogeneous Graph Convolutions via Positive Noncommutative Polynomials
Mingguo He, Zhewei Wei, Shikun Feng +4
Heterogeneous Graph Neural Networks (HGNNs) have gained significant popularity in various heterogeneous graph learning tasks. However, most existing HGNNs rely on spatial domain-ba…
Label Information Enhanced Fraud Detection against Low Homophily in Graphs
Yuchen Wang, Jinghui Zhang, Zhengjie Huang +9
Node classification is a substantial problem in graph-based fraud detection. Many existing works adopt Graph Neural Networks (GNNs) to enhance fraud detectors. While promising, cur…
Layout-aware Webpage Quality Assessment
Anfeng Cheng, Yiding Liu, Weibin Li +6
Identifying high-quality webpages is fundamental for real-world search engines, which can fulfil users' information need with the less cognitive burden. Early studies of \emph{webp…
ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding
Qiming Peng, Yinxu Pan, Wenjin Wang +12
Recent years have witnessed the rise and success of pre-training techniques in visually-rich document understanding. However, most existing methods lack the systematic mining and u…
Text detection and recognition based on a lensless imaging system
Yinger Zhang, Zhouyi Wu, Peiying Lin +4
Lensless cameras are characterized by several advantages (e.g., miniaturization, ease of manufacture, and low cost) as compared with conventional cameras. However, they have not be…
ERNIE-mmLayout: Multi-grained MultiModal Transformer for Document Understanding
Wenjin Wang, Zhengjie Huang, Bin Luo +8
Recent efforts of multimodal Transformers have improved Visually Rich Document Understanding (VrDU) tasks via incorporating visual and textual information. However, existing approa…
DuETA: Traffic Congestion Propagation Pattern Modeling via Efficient Graph Learning for ETA Prediction at Baidu Maps
Jizhou Huang, Zhengjie Huang, Xiaomin Fang +5
Estimated time of arrival (ETA) prediction, also known as travel time estimation, is a fundamental task for a wide range of intelligent transportation applications, such as navigat…
ERNIE-Search: Bridging Cross-Encoder with Dual-Encoder via Self On-the-fly Distillation for Dense Passage Retrieval
Yuxiang Lu, Yiding Liu, Jiaxiang Liu +8
Neural retrievers based on pre-trained language models (PLMs), such as dual-encoders, have achieved promising performance on the task of open-domain question answering (QA). Their…
Simple and Effective Relation-based Embedding Propagation for Knowledge Representation Learning
Huijuan Wang, Siming Dai, Weiyue Su +7
Relational graph neural networks have garnered particular attention to encode graph context in knowledge graphs (KGs). Although they achieved competitive performance on small KGs,…
ERNIE-GeoL: A Geography-and-Language Pre-trained Model and its Applications in Baidu Maps
Jizhou Huang, Haifeng Wang, Yibo Sun +4
Pre-trained models (PTMs) have become a fundamental backbone for downstream tasks in natural language processing and computer vision. Despite initial gains that were obtained by ap…
Graph4Rec: A Universal Toolkit with Graph Neural Networks for Recommender Systems
Weibin Li, Mingkai He, Zhengjie Huang +4
In recent years, owing to the outstanding performance in graph representation learning, graph neural network (GNN) techniques have gained considerable interests in many real-world…
NOTE: Solution for KDD-CUP 2021 WikiKG90M-LSC
Weiyue Su, Zeyang Fang, Hui Zhong +6
WikiKG90M in KDD Cup 2021 is a large encyclopedic knowledge graph, which could benefit various downstream applications such as question answering and recommender systems. Participa…
LiteGEM: Lite Geometry Enhanced Molecular Representation Learning for Quantum Property Prediction
Shanzhuo Zhang, Lihang Liu, Sheng Gao +6
In this report, we (SuperHelix team) present our solution to KDD Cup 2021-PCQM4M-LSC, a large-scale quantum chemistry dataset on predicting HOMO-LUMO gap of molecules. Our solution…
kk2018 at SemEval-2020 Task 9: Adversarial Training for Code-Mixing Sentiment Classification
Jiaxiang Liu, Xuyi Chen, Shikun Feng +5
Code switching is a linguistic phenomenon that may occur within a multilingual setting where speakers share more than one language. With the increasing communication between groups…
ERNIE at SemEval-2020 Task 10: Learning Word Emphasis Selection by Pre-trained Language Model
Zhengjie Huang, Shikun Feng, Weiyue Su +5
This paper describes the system designed by ERNIE Team which achieved the first place in SemEval-2020 Task 10: Emphasis Selection For Written Text in Visual Media. Given a sentence…
Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification
Yunsheng Shi, Zhengjie Huang, Shikun Feng +3
Graph neural network (GNN) and label propagation algorithm (LPA) are both message passing algorithms, which have achieved superior performance in semi-supervised classification. GN…
Online Robot Introspection via Wrench-based Action Grammars
Juan Rojas, Shuangqi Luo, Dingqiao Zhu +5
Robotic failure is all too common in unstructured robot tasks. Despite well-designed controllers, robots often fail due to unexpected events. How do robots measure unexpected event…
Chinese/English mixed Character Segmentation as Semantic Segmentation
Huabin Zheng, Jingyu Wang, Zhengjie Huang +2
OCR character segmentation for multilingual printed documents is difficult due to the diversity of different linguistic characters. Previous approaches mainly focus on monolingual…
Robot Introspection via Wrench-based Action Grammars
Juan Rojas, Zhengjie Huang, Shuangqi Luo +3
Robotic failure is all too common in unstructured robot tasks. Despite well designed controllers, robots often fail due to unexpected events. How do robots measure unexpected event…