Related papers: Process-Supervised LLM Recommenders via Flow-guide…

Supervised fine-tuning (SFT) has emerged as a crucial method for aligning large language models (LLMs) with human-annotated demonstrations. However, SFT, being an off-policy approach similar to behavior cloning, often struggles with…

Flow-based generative models have shown remarkable success in text-to-image generation, yet fine-tuning them with intermediate feedback remains challenging, especially for continuous-time flow matching models. Most existing approaches…

Modern instruction-tuned large language models (LLMs) have made remarkable progress in code generation. However, these LLMs fine-tuned with standard supervised fine-tuning (SFT) sometimes generate plausible-looking but functionally…

Recommender systems serve as foundational infrastructure in modern information ecosystems, helping users navigate digital content and discover items aligned with their preferences. At their core, recommender systems address a fundamental…

Supervised fine-tuning (SFT) is a fundamental post-training strategy to align Large Language Models (LLMs) with human intent. However, traditional SFT often ignores the one-to-many nature of language by forcing alignment with a single…

Finding effective prompts for language models (LMs) is critical yet notoriously difficult: the prompt space is combinatorially large, rewards are sparse due to expensive target-LM evaluation. Yet, existing RL-based prompt optimizers often…

We study the task of generating profitable Non-Fungible Token (NFT) images from user-input texts. Recent advances in diffusion models have shown great potential for image generation. However, existing works can fall short in generating…

When using supervised fine-tuning (SFT) to adapt large language models (LLMs) to specific domains, a significant challenge arises: should we use the entire SFT dataset for fine-tuning? Common practice often involves fine-tuning directly on…

Recent studies have explored integrating large language models (LLMs) into recommendation systems but face several challenges, including training-induced bias and bottlenecks from serialized architecture. To effectively address these…

Foundation models have demonstrated a great ability to achieve general human-level intelligence far beyond traditional approaches. As the technique keeps attracting attention from the AI community, an increasing number of foundation models…

Semantic understanding of popularity bias is a crucial yet underexplored challenge in recommender systems, where popular items are often favored at the expense of niche content. Most existing debiasing methods treat the semantic…

Reinforcement learning from human feedback (RLHF) has emerged as an effective approach to aligning large language models (LLMs) to human preferences. RLHF contains three steps, i.e., human preference collecting, reward learning, and policy…

Large Language Models have demonstrated outstanding performance across various downstream tasks and have been widely applied in multiple scenarios. Human-annotated preference data is used for training to further improve LLMs' performance,…

While methods exist for aligning flow matching models--a popular and effective class of generative models--with human preferences, existing approaches fail to achieve both adaptation efficiency and probabilistically sound prior…

Generative Flow Networks (GFlowNets) have been introduced as a method to sample a diverse set of candidates in an active learning context, with a training objective that makes them approximately sample in proportion to a given reward…

Diffusion models and flow matching have demonstrated remarkable success in text-to-image generation. While many existing alignment methods primarily focus on fine-tuning pre-trained generative models to maximize a given reward function,…

Generative Flow Networks (GFlowNets) are a family of probabilistic generative models that learn to sample compositional objects proportional to their rewards. One big challenge of GFlowNets is training them effectively when dealing with…

As humans increasingly share environments with diverse agents powered by RL, LLMs, and beyond, the ability to explain agent policies in natural language is vital for reliable coexistence. We introduce a general-purpose framework that trains…

Large language models are typically post-trained using supervised fine-tuning (SFT) and reinforcement learning (RL), yet effectively unifying efficient knowledge injection with robust generalization remains challenging. In this work, we…

Modern recommender systems aim to deeply understand users' complex preferences through their past interactions. While deep collaborative filtering approaches using Graph Neural Networks (GNNs) excel at capturing user-item relationships,…