Related papers: RLTP: Reinforcement Learning to Pace for Delayed I…

While Reinforcement Learning for Verifiable Rewards (RLVR) is powerful for training large reasoning models, its training dynamics harbor a critical challenge: RL overfitting, where models gain training rewards but lose generalization. Our…

The Internet of Things (IoT) signifies a revolutionary technological advancement, enhancing various applications through device interconnectivity while introducing significant challenges due to these devices' limited hardware and…

Reinforcement learning (RL) finetuning has become a key technique for enhancing the reasoning abilities of large language models (LLMs). However, its effectiveness critically depends on the selection of training data. Recent advances…

Motion forecasting for on-road traffic agents presents both a significant challenge and a critical necessity for ensuring safety in autonomous driving systems. In contrast to most existing data-driven approaches that directly predict future…

Relevance modeling is a critical component for enhancing user experience in search engines, with the primary objective of identifying items that align with users' queries. Traditional models only rely on the semantic congruence between…

Large Language Models (LLMs) have demonstrated impressive reasoning capabilities in complex problem-solving tasks, sparking growing interest in their application to preference reasoning in recommendation systems. Existing methods typically…

In this work, we introduce Reinforcement Pre-Training (RPT) as a new scaling paradigm for large language models and reinforcement learning (RL). Specifically, we reframe next-token prediction as a reasoning task trained using RL, where it…

Designing reward functions for continuous-control robotics often leads to subtle misalignments or reward hacking, especially in complex tasks. Preference-based RL mitigates some of these pitfalls by learning rewards from comparative…

To support complex search tasks, where the initial information requirements are complex or may change during the search, a search engine must adapt the information delivery as the user's information requirements evolve. To support this…

Learning-to-Rank (LTR) models trained from implicit feedback (e.g. clicks) suffer from inherent biases. A well-known one is the position bias -- documents in top positions are more likely to receive clicks due in part to their position…

Understanding real-world videos with complex semantics and long temporal dependencies remains a fundamental challenge in computer vision. Recent progress in multimodal large language models (MLLMs) has demonstrated strong capabilities in…

When using LLMs to rank items based on given criteria, or evaluate answers, the order of candidate items can influence the model's final decision. This sensitivity to item positioning in a LLM's prompt is known as position bias. Prior…

The aim of Reinforcement Learning (RL) in real-world applications is to create systems capable of making autonomous decisions by learning from their environment through trial and error. This paper emphasizes the importance of reward…

Click-Through Rate (CTR) prediction is crucial for Recommendation System(RS), aiming to provide personalized recommendation services for users in many aspects such as food delivery, e-commerce and so on. However, traditional RS relies on…

In this study, a real-time dispatching algorithm based on reinforcement learning is proposed and for the first time, is deployed in large scale. Current dispatching methods in ridehailing platforms are dominantly based on myopic or…

Advertising text plays a critical role in determining click-through rates (CTR) in online advertising. Large Language Models (LLMs) offer significant efficiency advantages over manual ad text creation. However, LLM-generated ad texts do not…

The emergence of smart Wi-Fi APs (Access Point), which are equipped with huge storage space, opens a new research area on how to utilize these resources at the edge network to improve users' quality of experience (QoE) (e.g., a short…

Click-through rate (CTR) prediction is a critical task in online advertising and recommender systems, relying on effective modeling of feature interactions. Explicit interactions capture predefined relationships, such as inner products, but…

Reinforcement learning (RL) has emerged as a key paradigm for aligning and optimizing large language models (LLMs). Standard approaches treat the LLM as the policy and apply RL directly over the full vocabulary space. However, this…

Reinforcement Learning (RL) algorithms for safety alignment of Large Language Models (LLMs), such as Direct Preference Optimization (DPO), encounter the challenge of distribution shift. Current approaches typically address this issue…