相关论文: TextAlign: Preference Alignment for Text Rendering…

While large language models (LLMs) excel at understanding and generating plain text, they are not tailored to handle hierarchical text structures or directly predict task-specific properties such as text rating. In fact, selectively and…

Reinforcement Learning (RL) has emerged as a transformative approach for aligning and enhancing Large Language Models (LLMs), addressing critical challenges in instruction following, ethical alignment, and reasoning capabilities. This…

The rapid advancement of text-to-image (T2I) diffusion models has enabled them to generate unprecedented results from given texts. However, as text inputs become longer, existing encoding methods like CLIP face limitations, and aligning the…

The field of advanced text-to-image generation is witnessing the emergence of unified frameworks that integrate powerful text encoders, such as CLIP and T5, with Diffusion Transformer backbones. Although there have been efforts to control…

This paper addresses the challenge of aligning large language models (LLMs) with diverse human preferences within federated learning (FL) environments, where standard methods often fail to adequately represent diverse viewpoints. We…

This paper focuses on the alignment of flow matching models with human preferences. A promising way is fine-tuning by directly backpropagating reward gradients through the differentiable generation process of flow matching. However,…

Recent text-to-image (T2I) models have benefited from large-scale and high-quality data, demonstrating impressive performance. However, these T2I models still struggle to produce images that are aesthetically pleasing, geometrically…

Aligning language models (LMs) with preferences is an important problem in natural language generation. A key challenge is that preferences are typically provided at the sequence level while LM training and generation both occur at the…

We introduce RewardFlow, an inversion-free framework that steers pretrained diffusion and flow-matching models at inference time through multi-reward Langevin dynamics. RewardFlow unifies complementary differentiable rewards for semantic…

The potential of reinforcement learning (RL) to deliver aligned and performant agents is partially bottlenecked by the reward engineering problem. One alternative to heuristic trial-and-error is preference-based RL (PbRL), where a reward…

Image scoring is a crucial task in numerous real-world applications. To trust a model's judgment, understanding its rationale is essential. This paper proposes a novel training method for Vision Language Models (VLMs) to generate not only…

Recent generative models have significantly advanced speech restoration tasks, yet their training objectives often misalign with human perceptual preferences, resulting in suboptimal quality. While post-training alignment has proven…

Differing from sentiment transfer, positive reframing seeks to substitute negative perspectives with positive expressions while preserving the original meaning. With the emergence of pre-trained language models (PLMs), it is possible to…

The reward model has become increasingly important in alignment, assessment, and data construction for large language models (LLMs). Most existing researchers focus on enhancing reward models through data improvements, following the…

Text-to-image models produce images that align well with natural language prompts, but compositional generation has long been a central challenge. Models often struggle to satisfy multiple concepts within a single prompt, frequently…

Recent advances in large language models (LLMs) have demonstrated significant progress in performing complex tasks. While Reinforcement Learning from Human Feedback (RLHF) has been effective in aligning LLMs with human preferences, it is…

Text-to-image (T2I) models achieve high-fidelity generation through extensive training on large datasets. However, these models may unintentionally pick up undesirable biases of their training data, such as over-representation of particular…

Large language model (LLM) alignment faces a critical dilemma when addressing multiple human preferences: improvements in one dimension frequently come at the expense of others, creating unavoidable trade-offs between competing objectives…

Flowcharts are typically presented as images, driving the trend of using vision-language models (VLMs) for end-to-end flowchart understanding. However, two key challenges arise: (i) Limited controllability--users have minimal influence over…

Aligning large language models to human preferences is inherently multidimensional, yet most pipelines collapse heterogeneous signals into a single optimizeable objective. We seek to answer what it would take to simultaneously align a model…