Accelerating science with AI and simulations
MIT Professor Rafael Gómez-Bombarelli discusses the transformative potential of AI in scientific research, emphasizing its role in materi...
Image, video, audio, and text generation
MIT Professor Rafael Gómez-Bombarelli discusses the transformative potential of AI in scientific research, emphasizing its role in materi...
Abstract page for arXiv paper 2603.14294: Seeking Physics in Diffusion Noise
Abstract page for arXiv paper 2512.22854: ByteLoom: Weaving Geometry-Consistent Human-Object Interactions through Progressive Curriculum ...
Abstract page for arXiv paper 2511.16105: Data-Efficient and Robust Trajectory Generation through Pathlet Dictionary Learning
Abstract page for arXiv paper 2603.23463: InverFill: One-Step Inversion for Enhanced Few-Step Diffusion Inpainting
Abstract page for arXiv paper 2510.08369: Guided Star-Shaped Masked Diffusion
Abstract page for arXiv paper 2603.23279: Emergence of Fragility in LLM-based Social Networks: the Case of Moltbook
Abstract page for arXiv paper 2603.23219: Decoding AI Authorship: Can LLMs Truly Mimic Human Style Across Literature and Politics?
Abstract page for arXiv paper 2603.23041: HUydra: Full-Range Lung CT Synthesis via Multiple HU Interval Generative Modelling
Abstract page for arXiv paper 2603.22468: SPDE Methods for Nonparametric Bayesian Posterior Contraction and Laplace Approximation
Abstract page for arXiv paper 2603.22492: Tiny Inference-Time Scaling with Latent Verifiers
Abstract page for arXiv paper 2603.23255: Permutation-Symmetrized Diffusion for Unconditional Molecular Generation
Abstract page for arXiv paper 2603.23140: DAK-UCB: Diversity-Aware Prompt Routing for LLMs and Generative Models
Abstract page for arXiv paper 2603.23086: Policy-based Tuning of Autoregressive Image Models with Instance- and Distribution-Level Rewards
Abstract page for arXiv paper 2603.23016: A Sobering Look at Tabular Data Generation via Probabilistic Circuits
Abstract page for arXiv paper 2603.22962: Asymptotic Learning Curves for Diffusion Models with Random Features Score and Manifold Data
Abstract page for arXiv paper 2603.22375: Three Creates All: You Only Sample 3 Steps
Abstract page for arXiv paper 2603.22943: PersonalQ: Select, Quantize, and Serve Personalized Diffusion Models for Efficient Inference
Abstract page for arXiv paper 2603.22364: MCLR: Improving Conditional Modeling in Visual Generative Models via Inter-Class Likelihood-Rat...
Abstract page for arXiv paper 2603.22844: PhySe-RPO: Physics and Semantics Guided Relative Policy Optimization for Diffusion-Based Surgic...
Abstract page for arXiv paper 2603.22316: ST-GDance++: A Scalable Spatial-Temporal Diffusion for Long-Duration Group Choreography
Abstract page for arXiv paper 2603.22309: UniFluids: Unified Neural Operator Learning with Conditional Flow-matching
Abstract page for arXiv paper 2603.22307: Full waveform inversion method based on diffusion model
Get the latest news, tools, and insights delivered to your inbox.
Daily or weekly digest • Unsubscribe anytime