Related papers: Ctrl-U: Robust Conditional Image Generation via Un…

Language models can learn a range of capabilities from unsupervised training on text corpora. However, to solve a particular problem (such as text summarization) it is typically necessary to fine-tune them on a task-specific dataset. It is…

Autonomous robotic tasks require actively perceiving the environment to achieve application-specific goals. In this paper, we address the problem of positioning an RGB camera to collect the most informative images to represent an unknown…

Recent advances in diffusion models have led to impressive image generation capabilities, but aligning these models with human preferences remains challenging. Reward-based fine-tuning using models trained on human feedback improves…

Uncertainty quantification (UQ) has emerged as a promising approach for detecting hallucinations and low-quality output of Large Language Models (LLMs). However, obtaining proper uncertainty scores is complicated by the conditional…

Recent advances in human preference alignment have significantly improved multimodal generation and understanding. A key approach is to train reward models that provide supervision signals for preference optimization. However, existing…

To align conditional text generation model outputs with desired behaviors, there has been an increasing focus on training the model using reinforcement learning (RL) with reward functions learned from human annotations. Under this…

Designing effective reward functions is a cornerstone of reinforcement learning (RL), yet it remains a challenging and labor-intensive process due to the inefficiencies and inconsistencies inherent in traditional methods. Existing methods…

Recent advances in text-to-image (T2I) generation via reinforcement learning (RL) have benefited from reward models that assess semantic alignment and visual quality. However, most existing reward models pay limited attention to…

Ensuring the safe exploration of reinforcement learning (RL) agents is critical for deployment in real-world systems. Yet existing approaches struggle to strike the right balance: methods that tightly enforce safety often cripple task…

Unsupervised image clustering methods often introduce alternative objectives to indirectly train the model and are subject to faulty predictions and overconfident results. To overcome these challenges, the current research proposes an…

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…

Text-to-image synthesis models require the ability to generate diverse images while maintaining stability. To overcome this challenge, a number of methods have been proposed, including the collection of prompt-image datasets and the…

Large-scale generative models have shown impressive image-generation capabilities, propelled by massive data. However, this often inadvertently leads to the generation of harmful or inappropriate content and raises copyright concerns.…

Recent progress in text-to-image generation has greatly advanced visual fidelity and creativity, but it has also imposed higher demands on prompt complexity-particularly in encoding intricate spatial relationships. In such cases, achieving…

Large language models (LLMs) are increasingly deployed as multi-step decision-making agents, where effective reward design is essential for guiding learning. Although recent work explores various forms of reward shaping and step-level…

In recent years, large-scale language models (LLMs) have gained attention for their impressive text generation capabilities. However, these models often face the challenge of "hallucination," which undermines their reliability. In this…

Uncertainty quantification plays an important role in achieving trustworthy and reliable learning-based computational imaging. Recent advances in generative modeling and Bayesian neural networks have enabled the development of…

Unpaired Image Captioning (UIC) has been developed to learn image descriptions from unaligned vision-language sample pairs. Existing works usually tackle this task using adversarial learning and visual concept reward based on reinforcement…

Deep unrolling is an emerging deep learning-based image reconstruction methodology that bridges the gap between model-based and purely deep learning-based image reconstruction methods. Although deep unrolling methods achieve…

Generating image descriptions in different languages is essential to satisfy users worldwide. However, it is prohibitively expensive to collect large-scale paired image-caption dataset for every target language which is critical for…