Related papers: DP$^2$O-SR: Direct Perceptual Preference Optimizat…
Existing methods for preference tuning of text-to-image (T2I) diffusion models often rely on computationally expensive generation steps to create positive and negative pairs of images. These approaches frequently yield training pairs that…
Diffusion models have demonstrated excellent performance for real-world image super-resolution (Real-ISR), albeit at high computational costs. Most existing methods are trying to derive one-step diffusion models from multi-step counterparts…
Recent advancements highlight the importance of GRPO-based reinforcement learning methods and benchmarking in enhancing text-to-image (T2I) generation. However, current methods using pointwise reward models (RM) for scoring generated images…
Diffusion models have achieved remarkable success in conditional image generation, yet their outputs often remain misaligned with human preferences. To address this, recent work has applied Direct Preference Optimization (DPO) to diffusion…
Diffusion Models have revolutionized the field of human motion generation by offering exceptional generation quality and fine-grained controllability through natural language conditioning. Their inherent stochasticity, that is the ability…
Text-to-Image (T2I) diffusion models are widely recognized for their ability to generate high-quality and diverse images based on text prompts. However, despite recent advances, these models are still prone to generating unsafe images…
Diffusion models represent the state-of-the-art in generative modeling. Due to their high training costs, many works leverage pre-trained diffusion models' powerful representations for downstream tasks, such as face super-resolution (FSR),…
Pre-trained diffusion models have shown great potential in real-world image super-resolution (Real-ISR) tasks by enabling high-resolution reconstructions. While one-step diffusion (OSD) methods significantly improve efficiency compared to…
We introduce a multi-scale Image Super Resolution (ISR) method building on recent advances in Visual Auto-Regressive (VAR) modeling. VAR models break image tokenization into additive, gradually increasing scales, using Residual Quantization…
Pre-trained text-to-image diffusion models are increasingly applied to real-world image super-resolution (Real-ISR) task. Given the iterative refinement nature of diffusion models, most existing approaches are computationally expensive.…
The success of Direct Preference Optimization (DPO) in mitigating hallucinations in Vision Language Models (VLMs) critically hinges on the true reward gaps within preference pairs. However, current methods, typically relying on ranking or…
Diffusion models have achieved remarkable success in image generation, yet their training is predominantly driven by full-reference objectives that enforce pixel-wise similarity to ground-truth images.Such supervision, while effective for…
Diffusion models, as a kind of powerful generative model, have given impressive results on image super-resolution (SR) tasks. However, due to the randomness introduced in the reverse process of diffusion models, the performances of…
Artificial Intelligence-Generated Content (AIGC) has made significant strides, with high-resolution text-to-image (T2I) generation becoming increasingly critical for improving users' Quality of Experience (QoE). Although…
Text-to-image (T2I) diffusion models have demonstrated impressive performance in generating high-fidelity images, largely enabled by text-guided inference. However, this advantage often comes with a critical drawback: limited diversity, as…
Video generation techniques have achieved remarkable advancements in visual quality, yet faithfully reproducing real-world physics remains elusive. Preference-based model post-training may improve physical consistency, but requires costly…
Blind face restoration usually synthesizes degraded low-quality data with a pre-defined degradation model for training, while more complex cases could happen in the real world. This gap between the assumed and actual degradation hurts the…
While recent advancements in Image Super-Resolution (SR) using diffusion models have shown promise in improving overall image quality, their application to scene text images has revealed limitations. These models often struggle with…
In the field of large language models (LLMs), aligning models with the diverse preferences of users is a critical challenge. Direct Preference Optimization (DPO) has played a key role in this area. It works by using pairs of preferences…
Recent developments in Direct Preference Optimization (DPO) allow large language models (LLMs) to function as implicit ranking models by maximizing the margin between preferred and non-preferred responses. In practice, user feedback on such…