Related papers: PosterReward: Unlocking Accurate Evaluation for Hi…

We present a discriminative multimodal reward model that scores all candidate responses in a single forward pass. Conventional discriminative reward models evaluate each response independently, requiring multiple forward passes, one for…

Recent advances in video reward models and post-training strategies have improved text-to-video (T2V) generation. While these models typically assess visual quality, motion quality, and text alignment, they often overlook key structural…

Movie posters are vital for captivating audiences, conveying themes, and driving market competition in the film industry. While traditional designs are laborious, intelligent generation technology offers efficiency gains and design…

Recent advances in multi-modal generative models have driven substantial improvements in image editing. However, current generative models still struggle with handling diverse and complex image editing tasks that require implicit reasoning,…

Video generation models have achieved remarkable progress, particularly excelling in realistic scenarios; however, their performance degrades notably in imaginative scenarios. These prompts often involve rarely co-occurring concepts with…

Preference learning from human feedback has the ability to align generative models with the needs of end-users. Human feedback is costly and time-consuming to obtain, which creates demand for data-efficient query selection methods. This…

Poster designing can benefit from synchronous feedback from target audiences. However, gathering audiences with diverse perspectives and reconciling them on design edits can be challenging. Recent generative AI models present opportunities…

Aligning Multimodal Large Language Models (MLLMs) requires reliable reward models, yet existing single-step evaluators can suffer from lazy judging, exploiting language priors over fine-grained visual verification. While rubric-based…

This study presents a generative optimization framework that builds on a fine-tuned diffusion model and reward-directed sampling to generate high-performance engineering designs. The framework adopts a parametric representation of the…

Well-designed prompts can guide text-to-image models to generate amazing images. However, the performant prompts are often model-specific and misaligned with user input. Instead of laborious human engineering, we propose prompt adaptation,…

Continuous emotional image generation (C-EICG) is emerging rapidly due to its ability to produce images aligned with both user descriptions and continuous emotional values. However, existing approaches lack emotional feedback from generated…

High-quality training triplets (instruction, original image, edited image) are essential for instruction-based image editing. Predominant training datasets (e.g., InsPix2Pix) are created using text-to-image generative models (e.g., Stable…

Multimodal large language models (MLLMs) have rapidly advanced from perception tasks to complex multi-step reasoning, yet reinforcement learning with verifiable rewards (RLVR) often leads to spurious reasoning since only the final-answer…

Video generation has witnessed significant advancements, yet evaluating these models remains a challenge. A comprehensive evaluation benchmark for video generation is indispensable for two reasons: 1) Existing metrics do not fully align…

While large language models have proven effective in a huge range of downstream applications, they often generate text that is problematic or lacks a desired attribute. In this paper, we introduce Reward-Augmented Decoding (RAD), a text…

Reinforcement learning (RL) can align language models with non-differentiable reward signals, such as human preferences. However, a major challenge arises from the sparsity of these reward signals - typically, there is only a single reward…

Text-to-motion generation, which synthesizes 3D human motions from text inputs, holds immense potential for applications in gaming, film, and robotics. Recently, diffusion-based methods have been shown to generate more diversity and…

Reward finetuning has emerged as a promising approach to aligning foundation models with downstream objectives. Remarkable success has been achieved in the language domain by using reinforcement learning (RL) to maximize rewards that…

Reinforcement learning (RL) has emerged as a promising paradigm for enhancing image editing and text-to-image (T2I) generation. However, current reward models, which act as critics during RL, often suffer from hallucinations and assign…

Modern text-to-image (T2I) models generate high-fidelity visuals but remain indifferent to individual user preferences. While existing reward models optimize for "average" human appeal, they fail to capture the inherent subjectivity of…