相关论文: Towards End-to-End Alignment of User Satisfaction …

Multi-Task Fusion plays a pivotal role in industrial short-video search systems by aggregating heterogeneous prediction signals into a unified ranking score. However, existing approaches predominantly optimize for immediate engagement…

Short video applications have attracted billions of users in recent years, fulfilling their various needs with diverse content. Users usually watch short videos on many topics on mobile devices in a short period of time, and give explicit…

We propose a novel End-to-end Multi-objective Ensemble Ranking framework (EMER) for the multi-objective ensemble ranking module, which is the most critical component of the short video recommendation system. EMER enhances personalization by…

User simulation is increasingly vital to develop and evaluate recommender systems (RSs). While Large Language Models (LLMs) offer promising avenues to simulate user behavior, they often struggle with the absence of specific task alignment…

Recommender selects and presents top-K items to the user at each online request, and a recommendation session consists of several sequential requests. Formulating a recommendation session as a Markov decision process and solving it by…

Sequential recommendation is one of the most important tasks in recommender systems, which aims to recommend the next interacted item with historical behaviors as input. Traditional sequential recommendation always mainly considers the…

Showing items that do not match search query intent degrades customer experience in e-commerce. These mismatches result from counterfactual biases of the ranking algorithms toward noisy behavioral signals such as clicks and purchases in the…

Visual Quality Assessment (QA) seeks to predict human perceptual judgments of visual fidelity. While recent multimodal large language models (MLLMs) show promise in reasoning about image and video quality, existing approaches mainly rely on…

In recommendation systems, users frequently engage in multiple types of behaviors, such as clicking, adding to a cart, and purchasing. However, with diversified behavior data, user behavior sequences will become very long in the short term,…

Short-video recommenders such as Douyin must exploit extremely long user behavior histories without breaking latency or cost budgets. We present an end-to-end industrial recommender system that scales long-sequence recommendation modeling…

Direct alignment algorithms have proven an effective step for aligning language models to human-desired behaviors. Current variants of the Direct Preference Optimization objective have focused on a strict setting where all tokens are…

The alignment of large language models (LLMs) with human preferences remains a key challenge. While post-training techniques like Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO) have achieved…

Traditional recommender systems (RecSys) primarily infer user preferences from implicit signals (such as clicks, watches, and purchases), often neglecting the rich explicit contextual feedback users provide through verbal text, like…

Despite the efficacy of network sparsity in alleviating the deployment strain of Large Language Models (LLMs), it endures significant performance degradation. Applying Low-Rank Adaptation (LoRA) to fine-tune the sparse LLMs offers an…

Recommender systems (RecSys) have become essential in modern society, driving user engagement and satisfaction across diverse online platforms. Most RecSys focuses on designing a powerful encoder to embed users and items into…

Effective personalization of LLMs is critical for a broad range of user-interfacing applications such as virtual assistants and content curation. Inspired by the strong in-context capabilities of LLMs, we propose few-shot preference…

Large-scale recommendations commonly adopt a multi-stage cascading ranking system paradigm to balance effectiveness and efficiency. Early Stage Ranking (ESR) systems utilize the "user-item decoupling" approach, where independently learned…

Sequential recommendation predicts users' next behaviors with their historical interactions. Recommending with longer sequences improves recommendation accuracy and increases the degree of personalization. As sequences get longer, existing…

Reinforcement Learning from Human Feedback and its variants excel in aligning with human intentions to generate helpful, harmless, and honest responses. However, most of them rely on costly human-annotated pairwise comparisons for…

We present \revise (\underline{Re}asoning with \underline{Vi}deo \underline{S}parsity), a multi-round agent for video question answering (VQA). Instead of uniformly sampling frames, \revise selects a small set of informative frames,…