English
Related papers

Related papers: SAGE: Sequence-level Adaptive Gradient Evolution f…

200 papers

A new gradient-based optimization approach by automatically scheduling the learning rate has been proposed recently, which is called Binary Forward Exploration (BFE). The Adaptive version of BFE has also been discussed thereafter. In this…

Machine Learning · Computer Science 2022-09-23 Xin Cao

Route recommendation systems commonly adopt a multi-stage pipeline involving fine-ranking and re-ranking to produce high-quality ordered recommendations. However, this paradigm faces three critical limitations. First, there is a…

Information Retrieval · Computer Science 2026-05-11 Chao Chen , Longfei Xu , Daohan Su , Tengfei Liu , Hanyu Guo , Yihai Duan , Kaikui Liu , Xiangxiang Chu

Direct preference optimization methods have emerged as a computationally efficient alternative to Reinforcement Learning from Human Feedback (RLHF) for aligning Large Language Models (LLMs). Latest approaches have streamlined the alignment…

Machine Learning · Computer Science 2026-02-04 Maksim Afanasyev , Illarion Iov

Generative recommendation models often struggle with two key challenges: (1) the superficial integration of collaborative signals, and (2) the decoupled fusion of multimodal features. These limitations hinder the creation of a truly…

Information Retrieval · Computer Science 2025-12-29 Yuzhen Lin , Hongyi Chen , Xuanjing Chen , Shaowen Wang , Ivonne Xu , Dongming Jiang

Generative recommendation systems have gained increasing attention as an innovative approach that directly generates item identifiers for recommendation tasks. Despite their potential, a major challenge is the effective construction of item…

Information Retrieval · Computer Science 2025-06-05 Enze Liu , Bowen Zheng , Cheng Ling , Lantao Hu , Han Li , Wayne Xin Zhao

Optimizing reranking in advertising feeds is a constrained combinatorial problem, requiring simultaneous maximization of platform revenue and preservation of user experience. Recent generative ranking methods enable listwise optimization…

Information Retrieval · Computer Science 2026-03-05 Chenfei Li , Hantao Zhao , Weixi Yao , Ruiming Huang , Rongrong Lu , Geng Tian , Dongying Kong

In recent years, Generative Adversarial Networks (GANs) have produced significantly improved results in speech enhancement (SE) tasks. They are difficult to train, however. In this work, we introduce several improvements to the GAN training…

Sound · Computer Science 2022-10-27 Vasily Zadorozhnyy , Qiang Ye , Kazuhito Koishida

Scalability issue plays a crucial role in productionizing modern recommender systems. Even lightweight architectures may suffer from high computational overload due to intermediate calculations, limiting their practicality in real-world…

Information Retrieval · Computer Science 2024-12-03 Gleb Mezentsev , Danil Gusak , Ivan Oseledets , Evgeny Frolov

Preference-based alignment objectives have been widely adopted, from RLHF-style pairwise learning in large language models to emerging applications in recommender systems. Yet, existing work rarely examines how Direct Preference…

Information Retrieval · Computer Science 2026-04-01 Hejin Huang , Jusheng Zhang , Kaitong Cai , Jian Wang , Rong Pan

Group Relative Policy Optimization (GRPO) methods for video generation like FlowGRPO remain far less reliable than their counterparts for language models and images. This gap arises because video generation has a complex solution space, and…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Mingzhe Zheng , Weijie Kong , Yue Wu , Dengyang Jiang , Yue Ma , Xuanhua He , Bin Lin , Kaixiong Gong , Zhao Zhong , Liefeng Bo , Qifeng Chen , Harry Yang

Recent breakthroughs in large language models (LLMs) have fundamentally shifted recommender systems from discriminative to generative paradigms, where user behavior modeling is achieved by generating target items conditioned on historical…

Information Retrieval · Computer Science 2025-10-15 Junfei Tan , Yuxin Chen , An Zhang , Junguang Jiang , Bin Liu , Ziru Xu , Han Zhu , Jian Xu , Bo Zheng , Xiang Wang

Generative molecular optimization aims to design molecules with properties surpassing those of existing compounds. However, such candidates are rare and expensive to evaluate, yielding sample efficiency essential. Additionally, surrogate…

In this paper, a new gradient-based optimization approach by automatically adjusting the learning rate is proposed. This approach can be applied to design non-adaptive learning rate and adaptive learning rate. Firstly, I will introduce the…

Machine Learning · Computer Science 2022-07-07 Xin Cao

As a new way of training generative models, Generative Adversarial Nets (GAN) that uses a discriminative model to guide the training of the generative model has enjoyed considerable success in generating real-valued data. However, it has…

Machine Learning · Computer Science 2017-08-28 Lantao Yu , Weinan Zhang , Jun Wang , Yong Yu

We propose a generic reward shaping approach for improving the rate of convergence in reinforcement learning (RL), called Self Improvement Based REwards, or SIBRE. The approach is designed for use in conjunction with any existing RL…

Machine Learning · Computer Science 2020-12-22 Somjit Nath , Richa Verma , Abhik Ray , Harshad Khadilkar

Inference-time scaling offers a versatile paradigm for aligning visual generative models with downstream objectives without parameter updates. However, existing approaches that optimize the high-dimensional initial noise suffer from severe…

Machine Learning · Computer Science 2026-02-04 Jinyan Ye , Zhongjie Duan , Zhiwen Li , Cen Chen , Daoyuan Chen , Yaliang Li , Yingda Chen

Large language models (LLMs), despite their extensive pretraining on diverse datasets, require effective alignment to human preferences for practical and reliable deployment. Conventional alignment methods typically employ off-policy…

Computation and Language · Computer Science 2025-07-29 Hyeonji Lee , Daejin Jo , Seohwan Yun , Sungwoong Kim

Preference optimization has become a central paradigm for aligning large language models with human feedback. Direct Preference Optimization (DPO) simplifies reinforcement learning from human feedback by directly optimizing pairwise…

Machine Learning · Computer Science 2026-05-05 Inoussa Mouiche

Many statistical problems involve optimization over a discrete parameter space having an unknown dimension. In such settings, gradient-based methods often fail due to the non-differentiability of the objective function or a non-convex or…

Applications · Statistics 2026-03-19 Mo Li , QiQi Lu , Robert Lund , Xueheng Shi

The recent success of large language models (LLMs) has renewed interest in whether recommender systems can achieve similar scaling benefits. Conventional recommenders, dominated by massive embedding tables, tend to plateau as embedding…

Information Retrieval · Computer Science 2025-10-29 Xiaoyu Kong , Leheng Sheng , Junfei Tan , Yuxin Chen , Jiancan Wu , An Zhang , Xiang Wang , Xiangnan He