Related papers: Scaling Multi-Agent Environment Co-Design with Dif…

We introduce Adjoint Sampling, a highly scalable and efficient algorithm for learning diffusion processes that sample from unnormalized densities, or energy functions. It is the first on-policy approach that allows significantly more…

Designing realistic multi-object scenes requires not only generating images, but also planning spatial layouts that respect semantic relations and physical plausibility. On one hand, while recent advances in diffusion models have enabled…

This article proposes a fundamental methodological shift in the modelling of policy interventions for sustainability transitions in order to account for complexity (e.g. self-reinforcing mechanism arising from multi-agent interactions) and…

Fine-tuning diffusion policies with reinforcement learning (RL) presents significant challenges. The long denoising sequence for each action prediction impedes effective reward propagation. Moreover, standard RL methods require millions of…

Robot swarms offer inherent robustness and the capacity to execute complex, collaborative tasks surpassing the capabilities of single-agent systems. Co-designing these systems is critical, as marginal improvements in individual performance…

Diffusion models, a powerful and universal generative AI technology, have achieved tremendous success in computer vision, audio, reinforcement learning, and computational biology. In these applications, diffusion models provide flexible…

In the landscape of generative artificial intelligence, diffusion-based models have emerged as a promising method for generating synthetic images. However, the application of diffusion models poses numerous challenges, particularly…

The emergence of diffusion models has significantly advanced generative AI, improving the quality, realism, and creativity of image and video generation. Among them, Stable Diffusion (StableDiff) stands out as a key model for text-to-image…

The growing deployment of decision-making agents in dynamic environments increases the demand for safety verification. While critical testing scenario generation has emerged as an appealing verification methodology, effectively balancing…

Classical paradigms for distributed learning, such as federated or decentralized gradient descent, employ consensus mechanisms to enforce homogeneity among agents. While these strategies have proven effective in i.i.d. scenarios, they can…

Inverse design problems are common in engineering and materials science. The forward direction, i.e., computing output quantities from design parameters, typically requires running a numerical simulation, such as a FEM, as an intermediate…

Diffusion and flow-based models have enabled significant progress in generation tasks across various modalities and have recently found applications in predictive learning. However, unlike typical generation tasks that encourage sample…

Prompt learning has demonstrated promising results in fine-tuning pre-trained multimodal models. However, the performance improvement is limited when applied to more complex and fine-grained tasks. The reason is that most existing methods…

Thanks to the rapid development of diffusion models, unprecedented progress has been witnessed in image synthesis. Prior works mostly rely on pre-trained linguistic models, but a text is often too abstract to properly specify all the…

Models for natural language and images benefit from data scaling behavior: the more data fed into the model, the better they perform. This 'better with more' phenomenon enables the effectiveness of large-scale pre-training on vast amounts…

A critical limitation in large-scale multi-agent systems is the cascading of errors. And without intermediate verification, downstream agents exacerbate upstream inaccuracies, resulting in significant quality degradation. To bridge this…

Large generative diffusion models have revolutionized text-to-image generation and offer immense potential for conditional generation tasks such as image enhancement, restoration, editing, and compositing. However, their widespread adoption…

Diffusion Transformer (DiT), a promising diffusion model for visual generation, demonstrates impressive performance but incurs significant computational overhead. Intriguingly, analysis of pre-trained DiT models reveals that global…

Constraint-based optimization is a cornerstone of robotics, enabling the design of controllers that reliably encode task and safety requirements such as collision avoidance or formation adherence. However, handcrafted constraints can fail…

Diffusion models excel at capturing the natural design spaces of images, molecules, DNA, RNA, and protein sequences. However, rather than merely generating designs that are natural, we often aim to optimize downstream reward functions while…