相关论文: A Production-Ready RL Framework for Personalized U…

The ranking utility function in an ad recommender system, which linearly combines predictions of various business goals, plays a central role in balancing values across the platform, advertisers, and users. Traditional manual tuning, while…

While foundation models have been exploited for various expert tasks through fine-tuning, any foundation model will become outdated due to its old knowledge or limited capability. Thus the underlying foundation model should be eventually…

Optimizing multiple objectives simultaneously is an important task for recommendation platforms to improve their performance. However, this task is particularly challenging since the relationships between different objectives are…

Determining consumer preferences and utility is a foundational challenge in economics. They are central in determining consumer behaviour through the utility-maximising consumer decision-making process. However, preferences and utilities…

As LLMs continue to scale, improving training efficiency increasingly depends on using data more effectively. Data selection addresses this problem by allocating a limited training budget to samples that best promote a target behavior.…

Parameter-Efficient Fine-Tuning (PEFT) is widely used for adapting Large Language Models (LLMs) for various tasks. Recently, there has been an increasing demand for fine-tuning a single LLM for multiple tasks because it requires overall…

Iterative data generation and model re-training can effectively align large language models(LLMs) to human preferences. The process of data sampling is crucial, as it significantly influences the success of policy improvement. Repeated…

Personalized large language models (LLMs) tailor content to individual preferences using user profiles or histories. However, existing parameter-efficient fine-tuning (PEFT) methods, such as the ``One-PEFT-Per-User'' (OPPU) paradigm,…

Scaling data and compute is critical to the success of modern ML. However, scaling demands predictability: we want methods to not only perform well with more compute or data, but also have their performance be predictable from small-scale…

Fine-tuning large pre-trained foundation models often yields excellent downstream performance but is prohibitively expensive when updating all parameters. Parameter-efficient fine-tuning (PEFT) methods such as LoRA alleviate this by…

Prompt-tuning has emerged as a promising method for adapting pre-trained models to downstream tasks or aligning with human preferences. Prompt learning is widely used in NLP but has limited applicability to RL due to the complex physical…

Methods for controlling large language models (LLMs), including local weight fine-tuning, LoRA-based adaptation, and activation-based interventions, are often studied in isolation, obscuring their connections and making comparison…

In Multi-Task Learning (MTL), tasks may compete and limit the performance achieved on each other, rather than guiding the optimization to a solution, superior to all its single-task trained counterparts. Since there is often not a unique…

Personalized generation with frozen large language models requires a conditioning signal that is both compact and current. Existing personalization methods typically retrieve or summarize user histories in text, or compress them into static…

Large Language Models (LLMs) have exhibited significant promise in recommender systems by empowering user profiles with their extensive world knowledge and superior reasoning capabilities. However, LLMs face challenges like unstable…

Multi-task trade-offs in machine learning can be addressed via Pareto Front Learning (PFL) methods that parameterize the Pareto Front (PF) with a single model. PFL permits to select the desired operational point during inference, contrary…

Physics-Informed Neural Networks (PINNs) have emerged as a powerful framework for solving partial differential equations (PDEs). However, their performance heavily relies on the strategy used to select training points. Conventional adaptive…

In this paper, we consider jointly optimizing cell load balance and network throughput via a reinforcement learning (RL) approach, where inter-cell handover (i.e., user association assignment) and massive MIMO antenna tilting are configured…

Reinforcement learning (RL) has become the dominant paradigm for improving the performance of language models on complex reasoning tasks. Despite the substantial empirical gains demonstrated by RL-based training methods like GRPO, a…

Parameter-efficient fine-tuning (PEFT) is an effective method for adapting pre-trained vision models to downstream tasks by tuning a small subset of parameters. Among PEFT methods, sparse tuning achieves superior performance by only…