Related papers: Generative Inverse Design of Metamaterials with Fu…

Retrieval-Augmented Generation (RAG) is widely used to ground large language models in external knowledge sources. However, when applied to heterogeneous corpora and multi-step queries, Naive RAG pipelines often degrade in quality due to…

Traditional Retrieval-Augmented Generation (RAG) methods are limited by their reliance on a fixed number of retrieved documents, often resulting in incomplete or noisy information that undermines task performance. Although recent adaptive…

Generative recommendation (GR) typically first quantizes continuous item embeddings into multi-level semantic IDs (SIDs), and then generates the next item via autoregressive decoding. Although existing methods are already competitive in…

Semantic ID (SID)-based recommendation is a promising paradigm for scaling sequential recommender systems, but existing methods largely follow a semantic-centric pipeline: item embeddings are learned from foundation models and discretized…

Multimodal Large Language Models (MLLMs) have emerged as a promising foundation for universal multimodal embeddings. Recent studies have shown that reasoning-driven generative multimodal embeddings can outperform discriminative embeddings…

Inverse design aims to find design parameters $x$ achieving target performance $y^*$. Generative approaches learn bidirectional mappings between designs and labels, enabling diverse solution sampling. However, standard conditional flow…

Inverse problems and inverse design in multiphase media, i.e., recovering or engineering microstructures to achieve target macroscopic responses, require operating on discrete-valued material fields, rendering the problem non-differentiable…

Inverse design, where we seek to design input variables in order to optimize an underlying objective function, is an important problem that arises across fields such as mechanical engineering to aerospace engineering. Inverse design is…

In-materia reservoir computing (RC) leverages the intrinsic physical responses of functional materials to perform complex computational tasks. Magnetic metamaterials are exciting candidates for RC due to their huge state space, nonlinear…

Image generation models (IGMs), while capable of producing impressive and creative content, often memorize a wide range of undesirable concepts from their training data, leading to the reproduction of unsafe content such as NSFW imagery and…

In online convex optimization it is well known that certain subclasses of objective functions are much easier than arbitrary convex functions. We are interested in designing adaptive methods that can automatically get fast rates in as many…

Visual perception in the brain largely depends on the organization of neuronal receptive fields. Although extensive research has delineated the coding principles of receptive fields, most studies have been constrained by their foundational…

Optimizing the synthesis of zeolites and exploring novel frameworks offer pivotal opportunities and challenges in materials design. While inverse design proves highly effective for simpler crystals, its application to intricate structures…

The task of designing optical multilayer thin-films regarding a given target is currently solved using gradient-based optimization in conjunction with methods that can introduce additional thin-film layers. Recently, Deep Learning and…

Retrieval-augmented generation (RAG) techniques have proven to be effective in integrating up-to-date information, mitigating hallucinations, and enhancing response quality, particularly in specialized domains. While many RAG approaches…

Metamaterial mechanisms are micro-architectured compliant structures that operate through the elastic deformation of specially designed flexible members. This study develops an efficient design methodology for compliant mechanisms using…

The rational design of molecules with desired properties is a long-standing challenge in chemistry. Generative neural networks have emerged as a powerful approach to sample novel molecules from a learned distribution. Here, we propose a…

Inverse Reinforcement Learning (IRL) describes the problem of learning an unknown reward function of a Markov Decision Process (MDP) from observed behavior of an agent. Since the agent's behavior originates in its policy and MDP policies…

Recent self-supervised contrastive learning provides an effective approach for unsupervised person re-identification (ReID) by learning invariance from different views (transformed versions) of an input. In this paper, we incorporate a…

This study presents a generative optimization framework that builds on a fine-tuned diffusion model and reward-directed sampling to generate high-performance engineering designs. The framework adopts a parametric representation of the…