Related papers: Subject-driven Text-to-Image Generation via Prefer…

Reinforcement Learning from Human/AI Feedback (RLHF/RLAIF) has been extensively utilized for preference alignment of text-to-image models. Existing methods face certain limitations in terms of both data and algorithm. For training data,…

A reliable reward function is essential for reinforcement learning (RL) in image generation. Most current RL approaches depend on pre-trained preference models that output scalar rewards to approximate human preferences. However, these…

Unified multimodal generation architectures that jointly produce text and images have recently emerged as a promising direction for text-to-image (T2I) synthesis. However, many existing systems rely on explicit modality switching,…

Large Language Models (LLMs) can generate code from natural language, but their performance is highly sensitive to prompt formulation. We propose a reinforcement-learning-based framework that models prompt refinement as a sequential…

We propose Soft Preference Optimization (SPO), a method for aligning generative models, such as Large Language Models (LLMs), with human preferences, without the need for a reward model. SPO optimizes model outputs directly over a…

Recent advancements in reinforcement learning from human feedback have shown that utilizing fine-grained token-level reward models can substantially enhance the performance of Proximal Policy Optimization (PPO) in aligning large language…

Recently, diffusion-based deep generative models (e.g., Stable Diffusion) have shown impressive results in text-to-image synthesis. However, current text-to-image models often require multiple passes of prompt engineering by humans in order…

The Bradley-Terry (BT) model is a common and successful practice in reward modeling for Large Language Model (LLM) alignment. However, it remains unclear why this model -- originally developed for multi-player stochastic game matching --…

Prompt design plays a crucial role in text-to-video (T2V) generation, yet user-provided prompts are often short, unstructured, and misaligned with training data, limiting the generative potential of diffusion-based T2V models. We present…

Reinforcement learning (RL) can improve the prompt following capability of text-to-image (T2I) models, yet obtaining high-quality reward signals remains challenging: CLIP Score is too coarse-grained, while VLM-based reward models (e.g.,…

Subject-driven text-to-image generation models create novel renditions of an input subject based on text prompts. Existing models suffer from lengthy fine-tuning and difficulties preserving the subject fidelity. To overcome these…

While deep reinforcement learning (RL) promises freedom from hand-labeled data, great successes, especially for Embodied AI, require significant work to create supervision via carefully shaped rewards. Indeed, without shaped rewards, i.e.,…

Recent flow matching models for text-to-image generation have achieved remarkable quality, yet their integration with reinforcement learning for human preference alignment remains suboptimal, hindering fine-grained reward-based…

Large Language Models (LLMs) aligned using Reinforcement Learning from Human Feedback (RLHF) have shown remarkable generation abilities in numerous tasks. However, collecting high-quality human preferences creates costly bottlenecks in…

Tabular language models can generate synthetic tables by modeling rows as token sequences, but they are typically trained once with supervised fine-tuning and then used as static synthesizers. This is limiting because next-token likelihood…

Current text-to-image (T2I) benchmarks evaluate models on rigid prompts, potentially underestimating true generative capabilities due to prompt sensitivity and creating biases that favor certain models while disadvantaging others. We…

Evaluating instruction-guided image edits requires rewards that reflect subtle human preferences, yet current reward models typically depend on large-scale preference annotation and additional model training. This creates a data-efficiency…

Traditional preference tuning methods for LLMs/Visual Generative Models often rely solely on reward model labeling, which can be opaque, offer limited insights into the rationale behind preferences, and are prone to issues such as reward…

The ability to train high-performing reward models with few-shot data is critical for enhancing the efficiency and scalability of Reinforcement Learning from Human Feedback (RLHF). We propose a data augmentation and expansion framework that…

Recently, we have witnessed great progress in image editing with natural language instructions. Several closed-source models like GPT-Image-1, Seedream, and Google-Nano-Banana have shown highly promising progress. However, the open-source…