相关论文: PIER: Permutation-Level Interest-Based End-to-End …

In settings such as e-recruitment and online dating, recommendation involves distributing limited opportunities, calling for novel approaches to quantify and enforce fairness. We introduce \emph{inferiority}, a novel (un)fairness measure…

Whole-page optimization (WPO) decides how search and recommendation results are surfaced to users, and large language models (LLMs) open a new route to it by treating page generation as sequence generation. Adapting LLMs to web-scale WPO,…

The Product Data Model (PDM) is an example of a data-centric approach to modelling information-intensive business processes, which offers exibility and facilitates process optimization. Because the approach is declarative in nature, there…

Large language models (LLMs) enhanced with retrieval-augmented generation (RAG) have introduced a new paradigm for web search. However, the limited context awareness of LLMs degrades their performance on RAG tasks. Existing methods to…

This study addresses critical industrial challenges in e-commerce product categorization, namely platform heterogeneity and the structural limitations of existing taxonomies, by developing and deploying a multimodal hierarchical…

We propose a multi-criteria Composite Index Method (CIM) to compare the performance of alternative approaches to solving an optimization problem. The CIM is convenient in those situations when neither approach dominates the other when…

In this work, we introduce PIPER: Primitive-Informed Preference-based Hierarchical reinforcement learning via Hindsight Relabeling, a novel approach that leverages preference-based learning to learn a reward model, and subsequently uses…

Optimization aims at selecting a feasible set of parameters in an attempt to solve a particular problem, being applied in a wide range of applications, such as operations research, machine learning fine-tuning, and control engineering,…

The motivations of users to make interactions can be divided into static preference and dynamic interest. To accurately model user representations over time, recent studies in sequential recommendation utilize information propagation and…

Personalized recommendation brings about novel challenges in ensuring fairness, especially in scenarios in which users are not the only stakeholders involved in the recommender system. For example, the system may want to ensure that items…

E-commerce search systems rely on modeling user behavior to estimate item relevance and user preference, which are typically assumed to be stable and independently learnable signals. However, in practice, user interactions are jointly…

Memory tiering provides a cost-effective solution to increase memory capacity, utilization, and even bandwidth. Memory tiering relies on system software for memory profiling, detection of frequently accessed pages, and page migration. Such…

Aligning large language models (LLMs) with human preferences is critical for real-world deployment, yet existing methods like RLHF face computational and stability challenges. While DPO establishes an offline paradigm with single…

Composed image retrieval aims to find an image that best matches a given multi-modal user query consisting of a reference image and text pair. Existing methods commonly pre-compute image embeddings over the entire corpus and compare these…

Reinforcement Learning (RL) has achieved impressive success in post-training Large Language Models (LLMs) and Vision-Language Models (VLMs), with on-policy algorithms such as PPO, GRPO, and REINFORCE++ serving as the dominant paradigm.…

This paper presents Perceptual Preference Optimization (PerPO), a perception alignment method aimed at addressing the visual discrimination challenges in generative pre-trained multimodal large language models (MLLMs). To align MLLMs with…

Sponsored search in e-commerce poses several unique and complex challenges. These challenges stem from factors such as the asymmetric language structure between search queries and product names, the inherent ambiguity in user search intent,…

Online advertising systems typically use a cascaded architecture to manage massive requests and candidate volumes, where the ranking stages allocate traffic based on eCPM (predicted CTR $\times$ Bid). With the increasing popularity of…

Intuitively, an ideal collaborative filtering (CF) model should learn from users' full rankings over all items to make optimal top-K recommendations. Due to the absence of such full rankings in practice, most CF models rely on pairwise loss…

Recently, tremendous strides have been made to align the generation of Large Language Models (LLMs) with human values to mitigate toxic or unhelpful content. Leveraging Reinforcement Learning from Human Feedback (RLHF) proves effective and…