相关论文: Reward driven workflows for unsupervised explainab…

Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a promising framework for improving reasoning abilities in Large Language Models (LLMs). However, policy optimized with binary verification prone to overlook…

Diffusion models have demonstrated strong generative capabilities across scientific domains, but often produce outputs that violate physical laws. We propose a new perspective by framing physics-informed generation as a sparse reward…

Diffusion-weighted MRI is nowadays performed routinely due to its prognostic ability, yet the quality of the scans are often unsatisfactory which can subsequently hamper the clinical utility. To overcome the limitations, here we propose a…

Current reinforcement learning from human feedback (RLHF) pipelines for large language model (LLM) alignment typically assign scalar rewards to sequences, using the final token as a surrogate indicator for the quality of the entire…

Field localization boosts nonlinear optical processes at the hot spots of metal nanostructures. Fano resonances can further enhance these "local" processes taking place at the hot spots. However, in conventional nonlinear materials, the…

We propose a new fast fully unsupervised method to discover semantic patterns. Our algorithm is able to hierarchically find visual categories and produce a segmentation mask where previous methods fail. Through the modeling of what is a…

In this paper, we propose a novel semi-supervised feature selection framework by mining correlations among multiple tasks and apply it to different multimedia applications. Instead of independently computing the importance of features for…

Supervised Learning has been successfully used to produce phase diagrams and identify phase boundaries when local order parameters are unavailable. Here, we apply unsupervised learning to this task. By using readily available clustering…

Discrete diffusion models have demonstrated great promise in modeling various sequence data, ranging from human language to biological sequences. Inspired by the success of RL in language models, there is growing interest in further…

Unsupervised reinforcement learning (URL) aims to pre-train agents by exploring diverse states or skills in reward-free environments, facilitating efficient adaptation to downstream tasks. As the agent cannot access extrinsic rewards during…

Self-supervised learning is a powerful paradigm for representation learning on unlabelled images. A wealth of effective new methods based on instance matching rely on data-augmentation to drive learning, and these have reached a rough…

Unsupervised localization and segmentation are long-standing robot vision challenges that describe the critical ability for an autonomous robot to learn to decompose images into individual objects without labeled data. These tasks are…

Ferroelectric polarization switching underpins the functional performance of a wide range of materials and devices, yet its dependence on complex local microstructural features renders systematic exploration by manual or grid-based…

How can a reinforcement learning (RL) agent prepare to solve downstream tasks if those tasks are not known a priori? One approach is unsupervised skill discovery, a class of algorithms that learn a set of policies without access to a reward…

Reinforcement learning fine-tuning has become the dominant approach for aligning diffusion models with human preferences. However, assessing images is intrinsically a multi-dimensional task, and multiple evaluation criteria need to be…

Ferroelectrics have a spontaneous electrical polarization that is arranged into domains and can be reversed by an externally applied field. This high versatility makes them useful in enabling components such as capacitors, sensors, and…

Unnormalized probability distributions are central to modeling complex physical systems across various scientific domains. Traditional sampling methods, such as Markov Chain Monte Carlo (MCMC), often suffer from slow convergence, critical…

Robotic tasks such as manipulation with visual inputs require image features that capture the physical properties of the scene, e.g., the position and configuration of objects. Recently, it has been suggested to learn such features in an…

Polarons are widespread in functional materials and are key to device performance in several technological applications. However, their effective impact on material behavior remains elusive, as condensed matter studies struggle to capture…

Selective Laser Melting (SLM) is a powder-bed additive manufacturing technique whose part quality depends critically on feedstock morphology. However, conventional powder characterization methods are low-throughput and qualitative, failing…