Related papers: HPSv3: Towards Wide-Spectrum Human Preference Scor…
Recent text-to-image generative models can generate high-fidelity images from text inputs, but the quality of these generated images cannot be accurately evaluated by existing evaluation metrics. To address this issue, we introduce Human…
Recent years have witnessed a rapid growth of deep generative models, with text-to-image models gaining significant attention from the public. However, existing models often generate images that do not align well with human preferences,…
Current metrics for text-to-image models typically rely on statistical metrics which inadequately represent the real preference of humans. Although recent work attempts to learn these preferences via human annotated images, they reduce the…
A reliable and comprehensive evaluation metric that aligns with manual preference assessments is crucial for conversational head video synthesis methods development. Existing quantitative evaluations often fail to capture the full…
Recent years have witnessed remarkable progress in 3D content generation. However, corresponding evaluation methods struggle to keep pace. Automatic approaches have proven challenging to align with human preferences, and the mixed…
Aligning Large Language Model (LLM) responses with human preferences is vital for building safe and controllable AI systems. While preference optimization methods based on Plackett-Luce (PL) and Bradley-Terry (BT) models have shown promise,…
Common image editing tasks typically adopt powerful generative diffusion models as the leading paradigm for real-world content editing. Meanwhile, although reinforcement learning (RL) methods such as Diffusion-DPO and Flow-GRPO have further…
Human mesh recovery (HMR) from a single RGB image is inherently ambiguous, as multiple 3D poses can correspond to the same 2D observation. Recent diffusion-based methods tackle this by generating various hypotheses, but often sacrifice…
Contemporary image generation systems have achieved high fidelity and superior aesthetic quality beyond basic text-image alignment. However, existing evaluation frameworks have failed to evolve in parallel. This study reveals that human…
Evaluating concept customization is challenging, as it requires a comprehensive assessment of fidelity to generative prompts and concept images. Moreover, evaluating multiple concepts is considerably more difficult than evaluating a single…
3D content creation from text prompts has shown remarkable success recently. However, current text-to-3D methods often generate 3D results that do not align well with human preferences. In this paper, we present a comprehensive framework,…
Preference datasets are essential for training general-domain, instruction-following language models with Reinforcement Learning from Human Feedback (RLHF). Each subsequent data release raises expectations for future data collection,…
Efficient text-to-image generation remains a challenging task due to the high computational costs associated with the multi-step sampling in diffusion models. Although distillation of pre-trained diffusion models has been successful in…
Visual generative models have achieved remarkable progress in synthesizing photorealistic images and videos, yet aligning their outputs with human preferences across critical dimensions remains a persistent challenge. Though reinforcement…
We present a comprehensive solution to learn and improve text-to-image models from human preference feedback. To begin with, we build ImageReward -- the first general-purpose text-to-image human preference reward model -- to effectively…
Multidimensional human understanding is essential for real-world applications such as film analysis and virtual digital humans, yet current LVLM benchmarks largely focus on single-task settings and lack fine-grained, human-centric…
Human mesh recovery (HMR) from a single image is inherently ill-posed due to depth ambiguity and occlusions. Probabilistic methods have tried to solve this by generating numerous plausible 3D human mesh predictions, but they often exhibit…
Human pose and shape (HPS) estimation methods have been extensively studied, with many demonstrating high zero-shot performance on in-the-wild images and videos. However, these methods often struggle in challenging scenarios involving…
Recent text-guided image editing (TIE) models have achieved remarkable progress, while many edited images still suffer from issues such as artifacts, unexpected editings, unaesthetic contents. Although some benchmarks and methods have been…
With the rapid development of AIGC technology, significant progress has been made in diffusion model-based technologies for text-to-image (T2I) and text-to-video (T2V). In recent years, a few studies have introduced the strategy of Direct…