Search Results for author: Kun Gai

Found 114 papers, 43 papers with code

A Survey of Interactive Generative Video

no code implementations30 Apr 2025 Jiwen Yu, Yiran Qin, Haoxuan Che, Quande Liu, Xintao Wang, Pengfei Wan, Di Zhang, Kun Gai, Hao Chen, Xihui Liu

Interactive Generative Video (IGV) has emerged as a crucial technology in response to the growing demand for high-quality, interactive video content across various domains.

Autonomous Driving multimodal interaction +1

FIM: Frequency-Aware Multi-View Interest Modeling for Local-Life Service Recommendation

no code implementations23 Apr 2025 Guoquan Wang, Qiang Luo, Weisong Hu, Pengfei Yao, Wencong Zeng, Guorui Zhou, Kun Gai

There are two main challenges in modeling users' periodic behaviors in the local-life service recommendation systems: 1) the diverse demands of users exhibit varying periodicities, which are difficult to distinguish as they are mixed in the behavior sequences; 2) the periodic behaviors of users are subject to dynamic changes due to factors such as holidays and promotional events.

Recommendation Systems

VLM as Policy: Common-Law Content Moderation Framework for Short Video Platform

no code implementations21 Apr 2025 Xingyu Lu, Tianke Zhang, Chang Meng, Xiaobei Wang, Jinpeng Wang, Yifan Zhang, Shisong Tang, Changyi Liu, Haojie Ding, Kaiyu Jiang, Kaiyu Tang, Bin Wen, Hai-Tao Zheng, Fan Yang, Tingting Gao, Di Zhang, Kun Gai

Offline experiments and large-scale online A/B test demonstrates the superiority of KuaiMod: KuaiMod achieves the best moderation performance on our benchmark.

Generative Auto-Bidding with Value-Guided Explorations

no code implementations20 Apr 2025 Jingtong Gao, Yewen Li, Shuai Mao, Nan Jiang, Yejing Wang, Qingpeng Cai, Fei Pan, Peng Jiang, Kun Gai, Bo An, Xiangyu Zhao

Auto-bidding, with its strong capability to optimize bidding decisions within dynamic and competitive online environments, has become a pivotal strategy for advertising platforms.

Reinforcement Learning (RL)

BBQRec: Behavior-Bind Quantization for Multi-Modal Sequential Recommendation

no code implementations9 Apr 2025 Kaiyuan Li, Rui Xiang, Yong Bai, Yongxiang Tang, Yanhua Cheng, Xialong Liu, Peng Jiang, Kun Gai

Multi-modal sequential recommendation systems leverage auxiliary signals (e. g., text, images) to alleviate data sparsity in user-item interactions.

Quantization Sequential Recommendation

CHIME: A Compressive Framework for Holistic Interest Modeling

no code implementations9 Apr 2025 Yong Bai, Rui Xiang, Kaiyuan Li, Yongxiang Tang, Yanhua Cheng, Xialong Liu, Peng Jiang, Kun Gai

CHIME demonstrates superior ranking performance across diverse datasets, establishing a robust solution for scalable holistic interest modeling in recommendation systems.

Contrastive Learning Quantization +1

LLM-Alignment Live-Streaming Recommendation

no code implementations7 Apr 2025 Yueyang Liu, Jiangxia Cao, Shen Wang, Shuang Wen, Xiang Chen, Xiangyu Wu, Shuang Yang, Zhaojie Liu, Kun Gai, Guorui Zhou

In recent years, integrated short-video and live-streaming platforms have gained massive global adoption, offering dynamic content creation and consumption.

Recommendation Systems

Any2Caption:Interpreting Any Condition to Caption for Controllable Video Generation

no code implementations31 Mar 2025 Shengqiong Wu, Weicai Ye, Jiahao Wang, Quande Liu, Xintao Wang, Pengfei Wan, Di Zhang, Kun Gai, Shuicheng Yan, Hao Fei, Tat-Seng Chua

To address the bottleneck of accurate user intent interpretation within the current video generation community, we present Any2Caption, a novel framework for controllable video generation under any condition.

Video Generation

FullDiT: Multi-Task Video Generative Foundation Model with Full Attention

no code implementations25 Mar 2025 Xuan Ju, Weicai Ye, Quande Liu, Qiulin Wang, Xintao Wang, Pengfei Wan, Di Zhang, Kun Gai, Qiang Xu

Current video generative foundation models primarily focus on text-to-video tasks, providing limited control for fine-grained video content creation.

Video Generation

Boosting Resolution Generalization of Diffusion Transformers with Randomized Positional Encodings

no code implementations24 Mar 2025 Cong Liu, Liang Hou, Mingwu Zheng, Xin Tao, Pengfei Wan, Di Zhang, Kun Gai

In this paper, we propose a novel two-dimensional randomized positional encodings (RPE-2D) framework that focuses on learning positional order of image patches instead of the specific distances between them, enabling seamless high- and low-resolution image generation without requiring high- and low-resolution image training.

Data Augmentation Image Cropping +2

DiffMoE: Dynamic Token Selection for Scalable Diffusion Transformers

no code implementations18 Mar 2025 Minglei Shi, Ziyang Yuan, Haotian Yang, Xintao Wang, Mingwu Zheng, Xin Tao, Wenliang Zhao, Wenzhao Zheng, Jie zhou, Jiwen Lu, Pengfei Wan, Di Zhang, Kun Gai

Diffusion models have demonstrated remarkable success in various image generation tasks, but their performance is often limited by the uniform processing of inputs across varying conditions and noise levels.

Text-to-Image Generation

Learning Cascade Ranking as One Network

no code implementations12 Mar 2025 Yunli Wang, Zhen Zhang, Zhiqiang Wang, Zixuan Yang, Yu Li, Jian Yang, Shiyang Wen, Peng Jiang, Kun Gai

Recent advances such as RankFlow and FS-LTR have introduced interaction-aware training paradigms but still struggle to 1) align training objectives with the goal of the entire cascade ranking (i. e., end-to-end recall) and 2) learn effective collaboration patterns for different stages.

Stick to Facts: Towards Fidelity-oriented Product Description Generation

no code implementations11 Mar 2025 Zhangming Chan, Xiuying Chen, Yongliang Wang, Juntao Li, Zhiqiang Zhang, Kun Gai, Dongyan Zhao, Rui Yan

Different from other text generation tasks, in product description generation, it is of vital importance to generate faithful descriptions that stick to the product attribute information.

Attribute Decoder +1

Creator-Side Recommender System: Challenges, Designs, and Applications

no code implementations25 Feb 2025 Xiaoshuang Chen, Yibo Wang, Yao Wang, Husheng Liu, Kaiqiao Zhan, Ben Wang, Kun Gai

To this end, we develop a creator-side recommender system, called DualRec, to answer the following question: how to find the most suitable users for each item to enhance the creators' experience?

Recommendation Systems

From Principles to Applications: A Comprehensive Survey of Discrete Tokenizers in Generation, Comprehension, Recommendation, and Information Retrieval

no code implementations18 Feb 2025 Jian Jia, Jingtong Gao, Ben Xue, Junhao Wang, Qingpeng Cai, Quan Chen, Xiangyu Zhao, Peng Jiang, Kun Gai

Discrete tokenizers have emerged as indispensable components in modern machine learning systems, particularly within the context of autoregressive modeling and large language models (LLMs).

Information Retrieval multimodal generation +2

Finedeep: Mitigating Sparse Activation in Dense LLMs via Multi-Layer Fine-Grained Experts

no code implementations18 Feb 2025 Leiyu Pan, Zhenpeng Su, Minxuan Lv, Yizhe Xiong, Xiangwen Zhang, Zijia Lin, Hui Chen, Jungong Han, Guiguang Ding, Cheng Luo, Di Zhang, Kun Gai, Deyi Xiong

Moreover, we find that Finedeep achieves optimal results when balancing depth and width, specifically by adjusting the number of expert sub-layers and the number of experts per sub-layer.

Efficient Exploration

CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation

no code implementations12 Feb 2025 Qinghe Wang, Yawen Luo, Xiaoyu Shi, Xu Jia, Huchuan Lu, Tianfan Xue, Xintao Wang, Pengfei Wan, Di Zhang, Kun Gai

In the first stage, we design an interactive workflow that allows users to intuitively construct 3D-aware conditional signals by positioning object bounding boxes and defining camera movements within the 3D space.

Object Text-to-Video Generation +1

Improving Video Generation with Human Feedback

no code implementations23 Jan 2025 Jie Liu, Gongye Liu, Jiajun Liang, Ziyang Yuan, Xiaokun Liu, Mingwu Zheng, Xiele Wu, Qiulin Wang, Wenyu Qin, Menghan Xia, Xintao Wang, Xiaohong Liu, Fei Yang, Pengfei Wan, Di Zhang, Kun Gai, Yujiu Yang, Wanli Ouyang

Video generation has achieved significant advances through rectified flow techniques, but issues like unsmooth motion and misalignment between videos and prompts persist.

Video Generation

ConceptMaster: Multi-Concept Video Customization on Diffusion Transformer Models Without Test-Time Tuning

no code implementations8 Jan 2025 Yuzhou Huang, Ziyang Yuan, Quande Liu, Qiulin Wang, Xintao Wang, Ruimao Zhang, Pengfei Wan, Di Zhang, Kun Gai

We identify two key challenges for this task: 1) the identity decoupling issue, where directly adopting existing customization methods inevitably mix identity attributes when handling multiple concepts simultaneously, and 2) the scarcity of high-quality video-entity pairs, which is crucial for training a model that can well represent and decouple various customized concepts in video generation.

Text-to-Video Generation Video Generation

CRM: Retrieval Model with Controllable Condition

no code implementations18 Dec 2024 Chi Liu, Jiangxia Cao, Rui Huang, Kuo Cai, Weifeng Ding, Qiang Luo, Kun Gai, Guorui Zhou

This modification enables the retrieval stage could fulfill the target gap with ranking model, enhancing the retrieval model ability to search item candidates satisfied the user interests and condition effectively.

model Recommendation Systems +2

Adaptive$^2$: Adaptive Domain Mining for Fine-grained Domain Adaptation Modeling

no code implementations11 Dec 2024 Wenxuan Sun, Zixuan Yang, Yunli Wang, Zhen Zhang, Zhiqiang Wang, Yu Li, Jian Yang, Yiming Yang, Shiyang Wen, Peng Jiang, Kun Gai

To the best of our knowledge, Adaptive$^2$ is the first approach to automatically learn both domain identification and adaptation in online advertising, opening new research directions for this area.

Domain Adaptation

Towards Precise Scaling Laws for Video Diffusion Transformers

no code implementations25 Nov 2024 Yuanyang Yin, Yaqi Zhao, Mingwu Zheng, Ke Lin, Jiarong Ou, Rui Chen, Victor Shea-Jay Huang, Jiahao Wang, Xin Tao, Pengfei Wan, Di Zhang, Baoqun Yin, Wentao Zhang, Kun Gai

Achieving optimal performance of video diffusion transformers within given data and compute budget is crucial due to their high training costs.

Enhancing Instruction-Following Capability of Visual-Language Models by Reducing Image Redundancy

no code implementations23 Nov 2024 Te Yang, Jian Jia, Xiangyu Zhu, Weisong Zhao, Bo wang, Yanhua Cheng, Yan Li, Shengyuan Liu, Quan Chen, Peng Jiang, Kun Gai, Zhen Lei

In this paper, we propose Visual-Modality Token Compression (VMTC) and Cross-Modality Attention Inhibition (CMAI) strategies to alleviate this gap between MLLMs and LLMs by inhibiting the influence of irrelevant visual tokens during content generation, increasing the instruction-following ability of the MLLMs while retaining their multimodal understanding capacity.

Instruction Following MME +2

Scaling Laws for Online Advertisement Retrieval

no code implementations20 Nov 2024 Yunli Wang, Zixuan Yang, Zhen Zhang, Zhiqiang Wang, Jian Yang, Shiyang Wen, Peng Jiang, Kun Gai

To the best of our knowledge, this is the first work to study the scaling laws for online advertisement retrieval of real-world systems, showing great potential for scaling law in advertising system optimization.

Retrieval

QARM: Quantitative Alignment Multi-Modal Recommendation at Kuaishou

no code implementations18 Nov 2024 Xinchen Luo, Jiangxia Cao, Tianyu Sun, Jinkai Yu, Rui Huang, Wei Yuan, Hezheng Lin, Yichen Zheng, Shiyao Wang, Qigen Hu, Changqing Qiu, JiaQi Zhang, Xu Zhang, Zhiheng Yan, Jingming Zhang, Simin Zhang, Mingxing Wen, Zhaojie Liu, Kun Gai, Guorui Zhou

In recent years, with the significant evolution of multi-modal large models, many recommender researchers realized the potential of multi-modal information for user interest modeling.

Multi-modal Recommendation

KuaiFormer: Transformer-Based Retrieval at Kuaishou

no code implementations15 Nov 2024 Chi Liu, Jiangxia Cao, Rui Huang, Kai Zheng, Qiang Luo, Kun Gai, Guorui Zhou

In large-scale content recommendation systems, retrieval serves as the initial stage in the pipeline, responsible for selecting thousands of candidate items from billions of options to pass on to ranking modules.

Recommendation Systems Retrieval

MARM: Unlocking the Future of Recommendation Systems through Memory Augmentation and Scalable Complexity

no code implementations14 Nov 2024 Xiao Lv, Jiangxia Cao, Shijie Guan, Xiaoyou Zhou, Zhiguang Qi, Yaqiang Zang, Ming Li, Ben Wang, Kun Gai, Guorui Zhou

Considering the above differences with LLM, we can draw a conclusion that: for a RecSys model, compared to model parameters, the computational complexity FLOPs is a more expensive factor that requires careful control.

Language Modeling Language Modelling +1

RecFlow: An Industrial Full Flow Recommendation Dataset

1 code implementation28 Oct 2024 Qi Liu, Kai Zheng, Rui Huang, Wuchao Li, Kuo Cai, Yuan Chai, Yanan Niu, Yiqun Hui, Bing Han, Na Mou, Hongning Wang, Wentian Bao, Yunen Yu, Guorui Zhou, Han Li, Yang song, Defu Lian, Kun Gai

Industrial recommendation systems (RS) rely on the multi-stage pipeline to balance effectiveness and efficiency when delivering items from a vast corpus to users.

Recommendation Systems Selection bias

Coarse-to-fine Dynamic Uplift Modeling for Real-time Video Recommendation

no code implementations22 Oct 2024 Chang Meng, Chenhao Zhai, Xueliang Wang, Shuchang Liu, Xiaoqiang Feng, Lantao Hu, Xiu Li, Han Li, Kun Gai

These two modules work together to dynamically identify and targeting specific user groups and applying treatments effectively.

Marketing

ERABAL: Enhancing Role-Playing Agents through Boundary-Aware Learning

no code implementations23 Sep 2024 Yihong Tang, Jiao Ou, Che Liu, Fuzheng Zhang, Di Zhang, Kun Gai

Role-playing is an emerging application in the field of Human-Computer Interaction (HCI), primarily implemented through the alignment training of a large language model (LLM) with assigned characters.

Language Modeling Language Modelling +1

HoME: Hierarchy of Multi-Gate Experts for Multi-Task Learning at Kuaishou

no code implementations10 Aug 2024 Xu Wang, Jiangxia Cao, Zhiyi Fu, Kun Gai, Guorui Zhou

(3) Expert Underfitting: In our services, we have dozens of behavior tasks that need to be predicted, but we find that some data-sparse prediction tasks tend to ignore their specific-experts and assign large weights to shared-experts.

Mixture-of-Experts Multi-Task Learning

TWIN V2: Scaling Ultra-Long User Behavior Sequence Modeling for Enhanced CTR Prediction at Kuaishou

no code implementations23 Jul 2024 Zihua Si, Lin Guan, Zhongxiang Sun, Xiaoxue Zang, Jing Lu, Yiqun Hui, Xingchao Cao, Zeyu Yang, Yichen Zheng, Dewei Leng, Kai Zheng, Chenbin Zhang, Yanan Niu, Yang song, Kun Gai

The significance of modeling long-term user interests for CTR prediction tasks in large-scale recommendation systems is progressively gaining attention among researchers and practitioners.

Click-Through Rate Prediction Recommendation Systems

Multi-Epoch learning with Data Augmentation for Deep Click-Through Rate Prediction

no code implementations27 Jun 2024 Zhongxiang Fan, Zhaocheng Liu, Jian Liang, Dongying Kong, Han Li, Peng Jiang, Shuang Li, Kun Gai

MEDA minimizes overfitting by reducing the dependency of the embedding layer on subsequent training data or the Multi-Layer Perceptron (MLP) layers, and achieves data augmentation through training the MLP with varied embedding spaces.

Click-Through Rate Prediction Continual Learning +1

Small Agent Can Also Rock! Empowering Small Language Models as Hallucination Detector

1 code implementation17 Jun 2024 Xiaoxue Cheng, Junyi Li, Wayne Xin Zhao, Hongzhi Zhang, Fuzheng Zhang, Di Zhang, Kun Gai, Ji-Rong Wen

Hallucination detection is a challenging task for large language models (LLMs), and existing studies heavily rely on powerful closed-source LLMs such as GPT-4.

2k Hallucination

Decoding at the Speed of Thought: Harnessing Parallel Decoding of Lexical Units for LLMs

no code implementations24 May 2024 Chenxi Sun, Hongzhi Zhang, Zijia Lin, Jingyuan Zhang, Fuzheng Zhang, Zhongyuan Wang, Bin Chen, Chengru Song, Di Zhang, Kun Gai, Deyi Xiong

The core of our approach is the observation that a pre-trained language model can confidently predict multiple contiguous tokens, forming the basis for a \textit{lexical unit}, in which these contiguous tokens could be decoded in parallel.

Code Generation Language Modeling +4

RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance

1 code implementation23 May 2024 Zhicheng Sun, Zhenhao Yang, Yang Jin, Haozhe Chi, Kun Xu, Liwei Chen, Hao Jiang, Yang song, Kun Gai, Yadong Mu

Our study shows that based on a recent rectified flow framework, the major limitation of vanilla classifier guidance in requiring a special classifier can be resolved with a simple fixed-point solution, allowing flexible personalization with off-the-shelf image discriminators.

Image Generation Personalized Image Generation

Modeling User Fatigue for Sequential Recommendation

1 code implementation20 May 2024 Nian Li, Xin Ban, Cheng Ling, Chen Gao, Lantao Hu, Peng Jiang, Kun Gai, Yong Li, Qingmin Liao

In this paper, we propose to model user Fatigue in interest learning for sequential Recommendations (FRec).

Contrastive Learning Sequential Recommendation

Full Stage Learning to Rank: A Unified Framework for Multi-Stage Systems

no code implementations8 May 2024 Kai Zheng, Haijun Zhao, Rui Huang, Beichuan Zhang, Na Mou, Yanan Niu, Yang song, Hongning Wang, Kun Gai

To address this issue, we propose an improved ranking principle for multi-stage systems, namely the Generalized Probability Ranking Principle (GPRP), to emphasize both the selection bias in each stage of the system pipeline as well as the underlying interest of users.

Information Retrieval Learning-To-Rank +3

Inductive-Deductive Strategy Reuse for Multi-Turn Instructional Dialogues

no code implementations17 Apr 2024 Jiao Ou, Jiayu Wu, Che Liu, Fuzheng Zhang, Di Zhang, Kun Gai

In this paper, we propose to explicitly capture the complex rules to help the user simulator pose diverse and in-depth instruction.

RecGPT: Generative Personalized Prompts for Sequential Recommendation via ChatGPT Training Paradigm

no code implementations6 Apr 2024 Yabin Zhang, Wenhui Yu, Erhan Zhang, Xu Chen, Lantao Hu, Peng Jiang, Kun Gai

For the model part, we adopt Generative Pre-training Transformer (GPT) as the sequential recommendation model and design a user modular to capture personalized information.

Natural Language Understanding Sequential Recommendation

Sequential Recommendation for Optimizing Both Immediate Feedback and Long-term Retention

1 code implementation4 Apr 2024 Ziru Liu, Shuchang Liu, Zijian Zhang, Qingpeng Cai, Xiangyu Zhao, Kesen Zhao, Lantao Hu, Peng Jiang, Kun Gai

In the landscape of Recommender System (RS) applications, reinforcement learning (RL) has recently emerged as a powerful tool, primarily due to its proficiency in optimizing long-term rewards.

Contrastive Learning Multi-Task Learning +2

Enhancing Role-playing Systems through Aggressive Queries: Evaluation and Improvement

no code implementations16 Feb 2024 Yihong Tang, Jiao Ou, Che Liu, Fuzheng Zhang, Di Zhang, Kun Gai

Experiments on models improved by RoleAD indicate that our adversarial dataset ameliorates this deficiency, with the improvements demonstrating a degree of generalizability in ordinary scenarios.

Dialogue Generation

Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization

1 code implementation5 Feb 2024 Yang Jin, Zhicheng Sun, Kun Xu, Liwei Chen, Hao Jiang, Quzhe Huang, Chengru Song, Yuliang Liu, Di Zhang, Yang song, Kun Gai, Yadong Mu

In light of recent advances in multimodal Large Language Models (LLMs), there is increasing attention to scaling them from image-text data to more informative real-world videos.

Science Question Answering Text-to-Video Generation +3

Future Impact Decomposition in Request-level Recommendations

1 code implementation29 Jan 2024 Xiaobei Wang, Shuchang Liu, Xueliang Wang, Qingpeng Cai, Lantao Hu, Han Li, Peng Jiang, Kun Gai, Guangming Xie

Furthermore, we show that a reward-based future decomposition strategy can better express the item-wise future impact and improve the recommendation accuracy in the long term.

Recommendation Systems

Just Ask One More Time! Self-Agreement Improves Reasoning of Language Models in (Almost) All Scenarios

no code implementations14 Nov 2023 Lei Lin, Jiayi Fu, Pengli Liu, Qingyang Li, Yan Gong, Junchen Wan, Fuzheng Zhang, Zhongyuan Wang, Di Zhang, Kun Gai

Although chain-of-thought (CoT) prompting combined with language models has achieved encouraging results on complex reasoning tasks, the naive greedy decoding used in CoT prompting usually causes the repetitiveness and local optimality.

All Decoder +1

Mixed Attention Network for Cross-domain Sequential Recommendation

1 code implementation14 Nov 2023 GuanYu Lin, Chen Gao, Yu Zheng, Jianxin Chang, Yanan Niu, Yang song, Kun Gai, Zhiheng Li, Depeng Jin, Yong Li, Meng Wang

Recent proposed cross-domain sequential recommendation models such as PiNet and DASL have a common drawback relying heavily on overlapped users in different domains, which limits their usage in practical recommender systems.

Sequential Recommendation

Inverse Learning with Extremely Sparse Feedback for Recommendation

1 code implementation14 Nov 2023 GuanYu Lin, Chen Gao, Yu Zheng, Yinfeng Li, Jianxin Chang, Yanan Niu, Yang song, Kun Gai, Zhiheng Li, Depeng Jin, Yong Li

In this paper, we propose a meta-learning method to annotate the unlabeled data from loss and gradient perspectives, which considers the noises in both positive and negative instances.

Meta-Learning

DialogBench: Evaluating LLMs as Human-like Dialogue Systems

1 code implementation3 Nov 2023 Jiao Ou, Junda Lu, Che Liu, Yihong Tang, Fuzheng Zhang, Di Zhang, Kun Gai

In this paper, we propose DialogBench, a dialogue evaluation benchmark that contains 12 dialogue tasks to probe the capabilities of LLMs as human-like dialogue systems should have.

Dialogue Evaluation

Adaptive Neural Ranking Framework: Toward Maximized Business Goal for Cascade Ranking Systems

no code implementations16 Oct 2023 Yunli Wang, Zhiqiang Wang, Jian Yang, Shiyang Wen, Dongying Kong, Han Li, Kun Gai

Concretely, we employ multi-task learning to adaptively combine the optimization of relaxed and full targets, which refers to metrics Recall@m@k and OPA respectively.

Learning-To-Rank Multi-Task Learning +1

KwaiYiiMath: Technical Report

no code implementations11 Oct 2023 Jiayi Fu, Lei Lin, Xiaoyang Gao, Pengli Liu, Zhengzong Chen, Zhirui Yang, ShengNan Zhang, Xue Zheng, Yan Li, Yuliang Liu, Xucheng Ye, Yiqiao Liao, Chao Liao, Bin Chen, Chengru Song, Junchen Wan, Zijia Lin, Fuzheng Zhang, Zhongyuan Wang, Di Zhang, Kun Gai

Recent advancements in large language models (LLMs) have demonstrated remarkable abilities in handling a variety of natural language processing (NLP) downstream tasks, even on mathematical tasks requiring multi-step reasoning.

Ranked #97 on Arithmetic Reasoning on GSM8K (using extra training data)

Arithmetic Reasoning GSM8K +1

AURO: Reinforcement Learning for Adaptive User Retention Optimization in Recommender Systems

no code implementations6 Oct 2023 Zhenghai Xue, Qingpeng Cai, Bin Yang, Lantao Hu, Peng Jiang, Kun Gai, Bo An

As the policy performance of RL is sensitive to environment drifts, the loss function enables the state abstraction to be reflective of environment changes and notify the recommendation policy to adapt accordingly.

Navigate Reinforcement Learning (RL) +1

Generative Retrieval with Semantic Tree-Structured Item Identifiers via Contrastive Learning

1 code implementation23 Sep 2023 Zihua Si, Zhongxiang Sun, Jiale Chen, Guozhang Chen, Xiaoxue Zang, Kai Zheng, Yang song, Xiao Zhang, Jun Xu, Kun Gai

To obtain efficiency and effectiveness, this paper introduces a generative retrieval framework, namely SEATER, which learns SEmAntic Tree-structured item identifiERs via contrastive learning.

Contrastive Learning Recommendation Systems +2

KuaiSim: A Comprehensive Simulator for Recommender Systems

1 code implementation NeurIPS 2023 Kesen Zhao, Shuchang Liu, Qingpeng Cai, Xiangyu Zhao, Ziru Liu, Dong Zheng, Peng Jiang, Kun Gai

For each task, KuaiSim also provides evaluation protocols and baseline recommendation algorithms that further serve as benchmarks for future research.

Reinforcement Learning (RL) Sequential Recommendation

Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization

1 code implementation9 Sep 2023 Yang Jin, Kun Xu, Liwei Chen, Chao Liao, Jianchao Tan, Quzhe Huang, Bin Chen, Chenyi Lei, An Liu, Chengru Song, Xiaoqiang Lei, Di Zhang, Wenwu Ou, Kun Gai, Yadong Mu

Specifically, we introduce a well-designed visual tokenizer to translate the non-linguistic image into a sequence of discrete tokens like a foreign language that LLM can read.

Language Modelling Large Language Model +1

A Large Language Model Enhanced Conversational Recommender System

no code implementations11 Aug 2023 Yue Feng, Shuchang Liu, Zhenghai Xue, Qingpeng Cai, Lantao Hu, Peng Jiang, Kun Gai, Fei Sun

For response generation, we utilize the generation ability of LLM as a language interface to better interact with users.

Language Modeling Language Modelling +4

Understanding and Modeling Passive-Negative Feedback for Short-video Sequential Recommendation

1 code implementation8 Aug 2023 Yunzhu Pan, Chen Gao, Jianxin Chang, Yanan Niu, Yang song, Kun Gai, Depeng Jin, Yong Li

To enhance the robustness of our model, we then introduce a multi-task learning module to simultaneously optimize two kinds of feedback -- passive-negative feedback and traditional randomly-sampled negative feedback.

Multi-Task Learning Sequential Recommendation

Graph Contrastive Learning with Generative Adversarial Network

no code implementations1 Aug 2023 Cheng Wu, Chaokun Wang, Jingcao Xu, Ziyang Liu, Kai Zheng, Xiaowei Wang, Yang song, Kun Gai

Specifically, we present GACN, a novel Generative Adversarial Contrastive learning Network for graph representation learning.

Contrastive Learning Data Augmentation +3

PANE-GNN: Unifying Positive and Negative Edges in Graph Neural Networks for Recommendation

no code implementations7 Jun 2023 Ziyang Liu, Chaokun Wang, Jingcao Xu, Cheng Wu, Kai Zheng, Yang song, Na Mou, Kun Gai

Recommender systems play a crucial role in addressing the issue of information overload by delivering personalized recommendations to users.

Denoising Graph Representation Learning +1

Generative Flow Network for Listwise Recommendation

1 code implementation4 Jun 2023 Shuchang Liu, Qingpeng Cai, Zhankui He, Bowen Sun, Julian McAuley, Dong Zheng, Peng Jiang, Kun Gai

In this work, we aim to learn a policy that can generate sufficiently diverse item lists for users while maintaining high recommendation quality.

Diversity Recommendation Systems +1

Multi-behavior Self-supervised Learning for Recommendation

1 code implementation22 May 2023 Jingcao Xu, Chaokun Wang, Cheng Wu, Yang song, Kai Zheng, Xiaowei Wang, Changping Wang, Guorui Zhou, Kun Gai

Secondly, existing methods utilizing self-supervised learning (SSL) to tackle the data sparsity neglect the serious optimization imbalance between the SSL task and the target task.

Graph Neural Network Self-Supervised Learning

When Search Meets Recommendation: Learning Disentangled Search Representation for Recommendation

1 code implementation18 May 2023 Zihua Si, Zhongxiang Sun, Xiao Zhang, Jun Xu, Xiaoxue Zang, Yang song, Kun Gai, Ji-Rong Wen

In our paper, we propose a Search-Enhanced framework for the Sequential Recommendation (SESRec) that leverages users' search interests for recommendation, by disentangling similar and dissimilar representations within S&R behaviors.

Contrastive Learning Disentanglement +1

Exploration and Regularization of the Latent Action Space in Recommendation

1 code implementation7 Feb 2023 Shuchang Liu, Qingpeng Cai, Bowen Sun, Yuhao Wang, Ji Jiang, Dong Zheng, Kun Gai, Peng Jiang, Xiangyu Zhao, Yongfeng Zhang

To overcome this challenge, we propose a hyper-actor and critic learning framework where the policy decomposes the item list generation process into a hyper-action inference step and an effect-action selection step.

Recommendation Systems

Multi-Task Recommendations with Reinforcement Learning

1 code implementation7 Feb 2023 Ziru Liu, Jiejie Tian, Qingpeng Cai, Xiangyu Zhao, Jingtong Gao, Shuchang Liu, Dayou Chen, Tonghao He, Dong Zheng, Peng Jiang, Kun Gai

To be specific, the RMTL structure can address the two aforementioned issues by (i) constructing an MTL environment from session-wise interactions and (ii) training multi-task actor-critic network structure, which is compatible with most existing MTL-based recommendation models, and (iii) optimizing and fine-tuning the MTL loss function using the weights generated by critic networks.

Multi-Task Learning Recommendation Systems +3

Disentangled Causal Embedding With Contrastive Learning For Recommender System

1 code implementation7 Feb 2023 Weiqi Zhao, Dian Tang, Xin Chen, Dawei Lv, Daoli Ou, Biao Li, Peng Jiang, Kun Gai

Most previous studies neglect user's conformity and entangle interest with it, which may cause the recommender systems fail to provide satisfying results.

Contrastive Learning Recommendation Systems

TWIN: TWo-stage Interest Network for Lifelong User Behavior Modeling in CTR Prediction at Kuaishou

2 code implementations5 Feb 2023 Jianxin Chang, Chenbin Zhang, Zhiyi Fu, Xiaoxue Zang, Lin Guan, Jing Lu, Yiqun Hui, Dewei Leng, Yanan Niu, Yang song, Kun Gai

And for the user-item cross features, we compress each into a one-dimentional bias term in the attention score calculation to save the computational cost.

Click-Through Rate Prediction

Two-Stage Constrained Actor-Critic for Short Video Recommendation

1 code implementation3 Feb 2023 Qingpeng Cai, Zhenghai Xue, Chi Zhang, Wanqi Xue, Shuchang Liu, Ruohan Zhan, Xueliang Wang, Tianyou Zuo, Wentao Xie, Dong Zheng, Peng Jiang, Kun Gai

One the one hand, the platforms aims at optimizing the users' cumulative watch time (main goal) in long term, which can be effectively optimized by Reinforcement Learning.

Recommendation Systems reinforcement-learning +2

Reinforcing User Retention in a Billion Scale Short Video Recommender System

no code implementations3 Feb 2023 Qingpeng Cai, Shuchang Liu, Xueliang Wang, Tianyou Zuo, Wentao Xie, Bin Yang, Dong Zheng, Peng Jiang, Kun Gai

In this paper, we choose reinforcement learning methods to optimize the retention as they are designed to maximize the long-term performance.

Recommendation Systems reinforcement-learning +2

PEPNet: Parameter and Embedding Personalized Network for Infusing with Personalized Prior Information

1 code implementation2 Feb 2023 Jianxin Chang, Chenbin Zhang, Yiqun Hui, Dewei Leng, Yanan Niu, Yang song, Kun Gai

By infusing personalized selection of Embedding and personalized modification of DNN parameters, PEPNet tailored to the interests of each individual obtains significant performance gains, with online improvements exceeding 1\% in multiple task metrics across multiple domains.

Recommendation Systems

PrefRec: Recommender Systems with Human Preferences for Reinforcing Long-term User Engagement

1 code implementation6 Dec 2022 Wanqi Xue, Qingpeng Cai, Zhenghai Xue, Shuo Sun, Shuchang Liu, Dong Zheng, Peng Jiang, Kun Gai, Bo An

Though promising, the application of RL heavily relies on well-designed rewards, but designing rewards related to long-term user engagement is quite difficult.

Recommendation Systems Reinforcement Learning (RL)

Real-time Short Video Recommendation on Mobile Devices

no code implementations20 Aug 2022 Xudong Gong, Qinlin Feng, Yuan Zhang, Jiangling Qin, Weijie Ding, Biao Li, Peng Jiang, Kun Gai

However, as users continue to watch videos and feedback, the changing context leads the ranking of the server-side recommendation system inaccurate.

Recommendation Systems Re-Ranking

ResAct: Reinforcing Long-term Engagement in Sequential Recommendation with Residual Actor

1 code implementation1 Jun 2022 Wanqi Xue, Qingpeng Cai, Ruohan Zhan, Dong Zheng, Peng Jiang, Kun Gai, Bo An

Meanwhile, reinforcement learning (RL) is widely regarded as a promising framework for optimizing long-term engagement in sequential recommendation.

Reinforcement Learning (RL) Sequential Recommendation

Truncation-Free Matching System for Display Advertising at Alibaba

no code implementations18 Feb 2021 Jin Li, Jie Liu, Shangzhou Li, Yao Xu, Ran Cao, Qi Li, Biye Jiang, Guan Wang, Han Zhu, Kun Gai, Xiaoqiang Zhu

When receiving a user request, matching system (i) finds the crowds that the user belongs to; (ii) retrieves all ads that have targeted those crowds.

TAG

Optimizing Multiple Performance Metrics with Deep GSP Auctions for E-commerce Advertising

no code implementations5 Dec 2020 Zhilin Zhang, Xiangyu Liu, Zhenzhe Zheng, Chenrui Zhang, Miao Xu, Junwei Pan, Chuan Yu, Fan Wu, Jian Xu, Kun Gai

In e-commerce advertising, the ad platform usually relies on auction mechanisms to optimize different performance metrics, such as user experience, advertiser utility, and platform revenue.

Exploration in Online Advertising Systems with Deep Uncertainty-Aware Learning

1 code implementation25 Nov 2020 Chao Du, Zhifeng Gao, Shuo Yuan, Lining Gao, Ziyan Li, Yifan Zeng, Xiaoqiang Zhu, Jian Xu, Kun Gai, Kuang-Chih Lee

In this paper, we propose a novel Deep Uncertainty-Aware Learning (DUAL) method to learn CTR models based on Gaussian processes, which can provide predictive uncertainty estimations while maintaining the flexibility of deep neural networks.

Click-Through Rate Prediction Gaussian Processes

Learning to Infer User Hidden States for Online Sequential Advertising

no code implementations3 Sep 2020 Zhaoqing Peng, Junqi Jin, Lan Luo, Yaodong Yang, Rui Luo, Jun Wang, Wei-Nan Zhang, Haiyang Xu, Miao Xu, Chuan Yu, Tiejian Luo, Han Li, Jian Xu, Kun Gai

To drive purchase in online advertising, it is of the advertiser's great interest to optimize the sequential advertising strategy whose performance and interpretability are both important.

Deep Reinforcement Learning

A Deep Prediction Network for Understanding Advertiser Intent and Satisfaction

no code implementations20 Aug 2020 Liyi Guo, Rui Lu, Haoqi Zhang, Junqi Jin, Zhenzhe Zheng, Fan Wu, Jin Li, Haiyang Xu, Han Li, Wenkai Lu, Jian Xu, Kun Gai

For e-commerce platforms such as Taobao and Amazon, advertisers play an important role in the entire digital ecosystem: their behaviors explicitly influence users' browsing and shopping experience; more importantly, advertiser's expenditure on advertising constitutes a primary source of platform revenue.

Marketing

COLD: Towards the Next Generation of Pre-Ranking System

2 code implementations31 Jul 2020 Zhe Wang, Liqin Zhao, Biye Jiang, Guorui Zhou, Xiaoqiang Zhu, Kun Gai

We name it COLD (Computing power cost-aware Online and Lightweight Deep pre-ranking system).

Recommendation Systems

Learning Optimal Tree Models Under Beam Search

1 code implementation ICML 2020 Jingwei Zhuo, Ziru Xu, Wei Dai, Han Zhu, Han Li, Jian Xu, Kun Gai

Retrieving relevant targets from an extremely large target set under computational limits is a common challenge for information retrieval and recommendation systems.

Information Retrieval Recommendation Systems +1

DCAF: A Dynamic Computation Allocation Framework for Online Serving System

no code implementations17 Jun 2020 Biye Jiang, Pengye Zhang, Rihan Chen, Binding Dai, Xinchen Luo, Yin Yang, Guan Wang, Guorui Zhou, Xiaoqiang Zhu, Kun Gai

These stages usually allocate resource manually with specific computing power budgets, which requires the serving configuration to adapt accordingly.

Recommendation Systems Retrieval

A Deep Recurrent Survival Model for Unbiased Ranking

1 code implementation30 Apr 2020 Jiarui Jin, Yuchen Fang, Wei-Nan Zhang, Kan Ren, Guorui Zhou, Jian Xu, Yong Yu, Jun Wang, Xiaoqiang Zhu, Kun Gai

Position bias is a critical problem in information retrieval when dealing with implicit yet biased user feedback data.

Information Retrieval model +3

Stick to the Facts: Learning towards a Fidelity-oriented E-Commerce Product Description Generation

no code implementations IJCNLP 2019 Zhangming Chan, Xiuying Chen, Yongliang Wang, Juntao Li, Zhiqiang Zhang, Kun Gai, Dongyan Zhao, Rui Yan

Different from other text generation tasks, in product description generation, it is of vital importance to generate faithful descriptions that stick to the product attribute information.

Attribute Decoder +1

Res-embedding for Deep Learning Based Click-Through Rate Prediction Modeling

no code implementations25 Jun 2019 Guorui Zhou, Kailun Wu, Weijie Bian, Zhao Yang, Xiaoqiang Zhu, Kun Gai

In this paper, we model user behavior using an interest delay model, study carefully the embedding mechanism, and obtain two important results: (i) We theoretically prove that small aggregation radius of embedding vectors of items which belongs to a same user interest domain will result in good generalization performance of deep CTR model.

Click-Through Rate Prediction

Practice on Long Sequential User Behavior Modeling for Click-Through Rate Prediction

2 code implementations22 May 2019 Qi Pi, Weijie Bian, Guorui Zhou, Xiaoqiang Zhu, Kun Gai

To our knowledge, this is one of the first industrial solutions that are capable of handling long sequential user behavior data with length scaling up to thousands.

Click-Through Rate Prediction Recommendation Systems

Lifelong Sequential Modeling with Personalized Memorization for User Response Prediction

1 code implementation2 May 2019 Kan Ren, Jiarui Qin, Yuchen Fang, Wei-Nan Zhang, Lei Zheng, Weijie Bian, Guorui Zhou, Jian Xu, Yong Yu, Xiaoqiang Zhu, Kun Gai

In order to tackle these challenges, in this paper, we propose a Hierarchical Periodic Memory Network for lifelong sequential modeling with personalized memorization of sequential patterns for each user.

Memorization

Improve Diverse Text Generation by Self Labeling Conditional Variational Auto Encoder

no code implementations26 Mar 2019 Yuchi Zhang, Yongliang Wang, Liping Zhang, Zhiqiang Zhang, Kun Gai

In fact, this objective term guides the encoder towards the "best encoder" of the decoder to enhance the expressiveness.

Decoder Diversity +1

Deep Interest Evolution Network for Click-Through Rate Prediction

15 code implementations11 Sep 2018 Guorui Zhou, Na Mou, Ying Fan, Qi Pi, Weijie Bian, Chang Zhou, Xiaoqiang Zhu, Kun Gai

Easy-to-use, Modular and Extendible package of deep-learning based CTR models. DeepFM, DeepInterestNetwork(DIN), DeepInterestEvolutionNetwork(DIEN), DeepCrossNetwork(DCN), AttentionalFactorizationMachine(AFM), Neural Factorization Machine(NFM), AutoInt

Click-Through Rate Prediction Deep Learning +1

Learning Adaptive Display Exposure for Real-Time Advertising

no code implementations10 Sep 2018 Weixun Wang, Junqi Jin, Jianye Hao, Chunjie Chen, Chuan Yu, Wei-Nan Zhang, Jun Wang, Xiaotian Hao, Yixi Wang, Han Li, Jian Xu, Kun Gai

In this paper, we investigate the problem of advertising with adaptive exposure: can we dynamically determine the number and positions of ads for each user visit under certain business constraints so that the platform revenue can be increased?

Reinforcement Learning

A Multi-Agent Reinforcement Learning Method for Impression Allocation in Online Display Advertising

no code implementations10 Sep 2018 Di Wu, Cheng Chen, Xun Yang, Xiujun Chen, Qing Tan, Jian Xu, Kun Gai

With this formulation, we derive the optimal impression allocation strategy by solving the optimal bidding functions for contracts.

Multi-agent Reinforcement Learning reinforcement-learning +2

Semantic Human Matting

2 code implementations5 Sep 2018 Quan Chen, Tiezheng Ge, Yanyu Xu, Zhiqiang Zhang, Xinxin Yang, Kun Gai

SHM is the first algorithm that learns to jointly fit both semantic information and high quality details with deep networks.

Image Matting

Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion Rate

6 code implementations21 Apr 2018 Xiao Ma, Liqin Zhao, Guan Huang, Zhi Wang, Zelin Hu, Xiaoqiang Zhu, Kun Gai

To the best of our knowledge, this is the first public dataset which contains samples with sequential dependence of click and conversion labels for CVR modeling.

Click-Through Rate Prediction Recommendation Systems +2

Budget Constrained Bidding by Model-free Reinforcement Learning in Display Advertising

no code implementations23 Feb 2018 Di Wu, Xiujun Chen, Xun Yang, Hao Wang, Qing Tan, Xiaoxun Zhang, Jian Xu, Kun Gai

Our analysis shows that the immediate reward from environment is misleading under a critical resource constraint.

Marketing reinforcement-learning +2

Learning Tree-based Deep Model for Recommender Systems

6 code implementations8 Jan 2018 Han Zhu, Xiang Li, Pengye Zhang, Guozheng Li, Jie He, Han Li, Kun Gai

In systems with large corpus, however, the calculation cost for the learnt model to predict all user-item preferences is tremendous, which makes full corpus retrieval extremely difficult.

Recommendation Systems Retrieval

Rocket Launching: A Universal and Efficient Framework for Training Well-performing Light Net

3 code implementations14 Aug 2017 Guorui Zhou, Ying Fan, Runpeng Cui, Weijie Bian, Xiaoqiang Zhu, Kun Gai

Models applied on real time response task, like click-through rate (CTR) prediction model, require high accuracy and rigorous response time.

Click-Through Rate Prediction

Deep Interest Network for Click-Through Rate Prediction

18 code implementations21 Jun 2017 Guorui Zhou, Chengru Song, Xiaoqiang Zhu, Ying Fan, Han Zhu, Xiao Ma, Yanghui Yan, Junqi Jin, Han Li, Kun Gai

In this way, user features are compressed into a fixed-length representation vector, in regardless of what candidate ads are.

Click-Through Rate Prediction Prediction

Learning Piece-wise Linear Models from Large Scale Data for Ad Click Prediction

3 code implementations18 Apr 2017 Kun Gai, Xiaoqiang Zhu, Han Li, Kai Liu, Zhe Wang

CTR prediction in real-world business is a difficult machine learning problem with large scale nonlinear sparse data.

Click-Through Rate Prediction Feature Engineering

Optimized Cost per Click in Taobao Display Advertising

no code implementations27 Feb 2017 Han Zhu, Junqi Jin, Chang Tan, Fei Pan, Yifan Zeng, Han Li, Kun Gai

Moreover, the platform has to be responsible for the business revenue and user experience.

Learning Kernels with Radiuses of Minimum Enclosing Balls

no code implementations NeurIPS 2010 Kun Gai, Guangyun Chen, Chang-Shui Zhang

Experiments show that our method significantly outperforms both SVM with the uniform combination of basis kernels and other state-of-art MKL approaches.

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