Related papers: Exploring Synthesizable Chemical Space with Iterat…
Generative models for image generation are now commonly used for a wide variety of applications, ranging from guided image generation for entertainment to solving inverse problems. Nonetheless, training a generator is a non-trivial feat…
Collecting and annotating datasets for pixel-level semantic segmentation tasks are highly labor-intensive. Data augmentation provides a viable solution by enhancing model generalization without additional real-world data collection.…
While generative models have become powerful tools for image synthesis, they are typically optimized for executing carefully crafted textual prompts, offering limited support for the open-ended visual exploration that often precedes idea…
Text-to-image (T2I) models have achieved remarkable progress, yet they continue to struggle with complex prompts that require simultaneously handling multiple objects, relations, and attributes. Existing inference-time strategies, such as…
Adeno-associated viral (AAV) vectors are widely used delivery platforms in gene therapy, and the design of improved capsids is key to expanding their therapeutic potential. A central challenge in AAV bioengineering, as in protein design…
Representation (feature) space is an environment where data points are vectorized, distances are computed, patterns are characterized, and geometric structures are embedded. Extracting a good representation space is critical to address the…
Molecular machine learning has gained popularity with the advancements of geometric deep learning. In parallel, retrieval-augmented generation has become a principled approach commonly used with language models. However, the optimal…
How should future neural reasoning systems implement extended computation? Recursive Reasoning Models (RRMs) offer a promising alternative to autoregressive sequence extension by performing iterative latent-state refinement with shared…
Automated generation of high-quality media presentations is challenging, requiring robust content extraction, narrative planning, visual design, and overall quality optimization. Existing methods often produce presentations with logical…
Scene synthesis and editing has emerged as a promising direction in computer graphics. Current trained approaches for 3D indoor scene generation either oversimplify object semantics through one-hot class encodings (e.g., 'chair' or…
De novo molecule design has become a highly active research area, advanced significantly through the use of state-of-the-art generative models. Despite these advances, several fundamental questions remain unanswered as the field…
Synthesizing photo-realistic visual observations from an ego vehicle's driving trajectory is a critical step towards scalable training of self-driving models. Reconstruction-based methods create 3D scenes from driving logs and synthesize…
In this paper, we develop an iterative scheme to construct multiscale basis functions within the framework of the Constraint Energy Minimizing Generalized Multiscale Finite Element Method (CEM-GMsFEM) for the mixed formulation. The…
Stepwise inference protocols, such as scratchpads and chain-of-thought, help language models solve complex problems by decomposing them into a sequence of simpler subproblems. Despite the significant gain in performance achieved via these…
Multi-channel speech enhancement aims to recover clean speech from noisy multi-channel recordings. Most deep learning methods employ discriminative training, which can lead to non-linear distortions from regression-based objectives,…
Reinforcement learning with verifiable rewards (RLVR) has emerged as a promising approach for training reasoning language models (RLMs) by leveraging supervision from verifiers. Although verifier implementation is easier than solution…
Retrieval-Augmented Generation (RAG) systems face significant performance gaps when applied to technical domains requiring precise information extraction from complex documents. Current evaluation methodologies relying on document-level…
LLMs have fundamentally transformed dense retrieval, upgrading backbones from discriminative encoders to generative architectures. However, a critical disconnect remains: while LLMs possess strong reasoning capabilities, current retrievers…
In this paper, we introduce Random Path Generative Adversarial Network (RPGAN) -- an alternative design of GANs that can serve as a tool for generative model analysis. While the latent space of a typical GAN consists of input vectors,…
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…