Arash Vahdat
YOU?
Author Swipe
View article: BoltzGen: Toward Universal Binder Design
BoltzGen: Toward Universal Binder Design Open
We introduce BoltzGen , an all-atom generative model for designing proteins and peptides across all modalities to bind a wide range of biomolecular targets. BoltzGen builds strong structural reasoning capabilities about target-binder inter…
View article: Rethinking Molecule Synthesizability with Chain-of-Reaction
Rethinking Molecule Synthesizability with Chain-of-Reaction Open
A well-known pitfall of molecular generative models is that they are not guaranteed to generate synthesizable molecules. There have been considerable attempts to address this problem, but given the exponentially large combinatorial space o…
View article: Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and Inference
Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and Inference Open
Solving stochastic optimal control problems with quadratic control costs can be viewed as approximating a target path space measure, e.g. via gradient-based optimization. In practice, however, this optimization is challenging in particular…
View article: La-Proteina: Atomistic Protein Generation via Partially Latent Flow Matching
La-Proteina: Atomistic Protein Generation via Partially Latent Flow Matching Open
Recently, many generative models for de novo protein structure design have emerged. Yet, only few tackle the difficult task of directly generating fully atomistic structures jointly with the underlying amino acid sequence. This is challeng…
View article: Elucidated Rolling Diffusion Models for Probabilistic Forecasting of Complex Dynamics
Elucidated Rolling Diffusion Models for Probabilistic Forecasting of Complex Dynamics Open
Diffusion models are a powerful tool for probabilistic forecasting, yet most applications in high-dimensional complex systems predict future states individually. This approach struggles to model complex temporal dependencies and fails to e…
View article: Esoteric Language Models
Esoteric Language Models Open
Diffusion-based language models offer a compelling alternative to autoregressive (AR) models by enabling parallel and controllable generation. Among this family of models, Masked Diffusion Models (MDMs) achieve the strongest performance bu…
View article: Climate in a Bottle: Towards a Generative Foundation Model for the Kilometer-Scale Global Atmosphere
Climate in a Bottle: Towards a Generative Foundation Model for the Kilometer-Scale Global Atmosphere Open
Climate modeling is reaching unprecedented resolution, producing petabytes of data. AI climate model emulators offer a path to computationally cheap analysis, enabling new scientific insight and scenario planning. Recent advances show prom…
View article: On Equivariance and Fast Sampling in Video Diffusion Models Trained with Warped Noise
On Equivariance and Fast Sampling in Video Diffusion Models Trained with Warped Noise Open
Temporally consistent video-to-video generation is critical for applications such as style transfer and upsampling. In this paper, we provide a theoretical analysis of warped noise - a recently proposed technique for training video diffusi…
View article: Proteina: Scaling Flow-based Protein Structure Generative Models
Proteina: Scaling Flow-based Protein Structure Generative Models Open
Recently, diffusion- and flow-based generative models of protein structures have emerged as a powerful tool for de novo protein design. Here, we develop Proteina, a new large-scale flow-based protein backbone generator that utilizes hierar…
View article: Residual corrective diffusion modeling for km-scale atmospheric downscaling
Residual corrective diffusion modeling for km-scale atmospheric downscaling Open
State of the art for weather and climate hazard prediction requires expensive km-scale numerical simulations. Here, a generative diffusion model is explored for downscaling global inputs to km-scale, as a cost-effective alternative. The mo…
View article: Not-So-Optimal Transport Flows for 3D Point Cloud Generation
Not-So-Optimal Transport Flows for 3D Point Cloud Generation Open
Learning generative models of 3D point clouds is one of the fundamental problems in 3D generative learning. One of the key properties of point clouds is their permutation invariance, i.e., changing the order of points in a point cloud does…
View article: A2SB: Audio-to-Audio Schrodinger Bridges
A2SB: Audio-to-Audio Schrodinger Bridges Open
Real-world audio is often degraded by numerous factors. This work presents an audio restoration model tailored for high-res music at 44.1kHz. Our model, Audio-to-Audio Schrödinger Bridges (A2SB), is capable of both bandwidth extension (pre…
View article: BlobGEN-Vid: Compositional Text-to-Video Generation with Blob Video Representations
BlobGEN-Vid: Compositional Text-to-Video Generation with Blob Video Representations Open
Existing video generation models struggle to follow complex text prompts and synthesize multiple objects, raising the need for additional grounding input for improved controllability. In this work, we propose to decompose videos into visua…
View article: GenMol: A Drug Discovery Generalist with Discrete Diffusion
GenMol: A Drug Discovery Generalist with Discrete Diffusion Open
Drug discovery is a complex process that involves multiple stages and tasks. However, existing molecular generative models can only tackle some of these tasks. We present Generalist Molecular generative model (GenMol), a versatile framewor…
View article: Molecule Generation with Fragment Retrieval Augmentation
Molecule Generation with Fragment Retrieval Augmentation Open
Fragment-based drug discovery, in which molecular fragments are assembled into new molecules with desirable biochemical properties, has achieved great success. However, many fragment-based molecule generation methods show limited explorati…
View article: Energy-Based Diffusion Language Models for Text Generation
Energy-Based Diffusion Language Models for Text Generation Open
Despite remarkable progress in autoregressive language models, alternative generative paradigms beyond left-to-right generation are still being actively explored. Discrete diffusion models, with the capacity for parallel generation, have r…
View article: Warped Diffusion: Solving Video Inverse Problems with Image Diffusion Models
Warped Diffusion: Solving Video Inverse Problems with Image Diffusion Models Open
Using image models naively for solving inverse video problems often suffers from flickering, texture-sticking, and temporal inconsistency in generated videos. To tackle these problems, in this paper, we view frames as continuous functions …
View article: Truncated Consistency Models
Truncated Consistency Models Open
Consistency models have recently been introduced to accelerate sampling from diffusion models by directly predicting the solution (i.e., data) of the probability flow ODE (PF ODE) from initial noise. However, the training of consistency mo…
View article: Heavy-Tailed Diffusion Models
Heavy-Tailed Diffusion Models Open
Diffusion models achieve state-of-the-art generation quality across many applications, but their ability to capture rare or extreme events in heavy-tailed distributions remains unclear. In this work, we show that traditional diffusion and …
View article: Stochastic Flow Matching for Resolving Small-Scale Physics
Stochastic Flow Matching for Resolving Small-Scale Physics Open
Conditioning diffusion and flow models have proven effective for super-resolving small-scale details in natural images.However, in physical sciences such as weather, super-resolving small-scale details poses significant challenges due to: …
View article: Elucidating Optimal Reward-Diversity Tradeoffs in Text-to-Image Diffusion Models
Elucidating Optimal Reward-Diversity Tradeoffs in Text-to-Image Diffusion Models Open
Text-to-image (T2I) diffusion models have become prominent tools for generating high-fidelity images from text prompts. However, when trained on unfiltered internet data, these models can produce unsafe, incorrect, or stylistically undesir…
View article: Kilometer-Scale Convection Allowing Model Emulation using Generative Diffusion Modeling
Kilometer-Scale Convection Allowing Model Emulation using Generative Diffusion Modeling Open
Storm-scale convection-allowing models (CAMs) are an important tool for predicting the evolution of thunderstorms and mesoscale convective systems that result in damaging extreme weather. By explicitly resolving convective dynamics within …
View article: DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latents
DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latents Open
Diffusion models (DMs) have revolutionized generative learning. They utilize a diffusion process to encode data into a simple Gaussian distribution. However, encoding a complex, potentially multimodal data distribution into a single contin…
View article: Aligning Target-Aware Molecule Diffusion Models with Exact Energy Optimization
Aligning Target-Aware Molecule Diffusion Models with Exact Energy Optimization Open
Generating ligand molecules for specific protein targets, known as structure-based drug design, is a fundamental problem in therapeutics development and biological discovery. Recently, target-aware generative models, especially diffusion m…
View article: CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation
CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation Open
Recently video diffusion models have emerged as expressive generative tools for high-quality video content creation readily available to general users. However, these models often do not offer precise control over camera poses for video ge…
View article: DiffUHaul: A Training-Free Method for Object Dragging in Images
DiffUHaul: A Training-Free Method for Object Dragging in Images Open
Text-to-image diffusion models have proven effective for solving many image editing tasks. However, the seemingly straightforward task of seamlessly relocating objects within a scene remains surprisingly challenging. Existing methods addre…
View article: Compositional Text-to-Image Generation with Dense Blob Representations
Compositional Text-to-Image Generation with Dense Blob Representations Open
Existing text-to-image models struggle to follow complex text prompts, raising the need for extra grounding inputs for better controllability. In this work, we propose to decompose a scene into visual primitives - denoted as dense blob rep…
View article: AGG: Amortized Generative 3D Gaussians for Single Image to 3D
AGG: Amortized Generative 3D Gaussians for Single Image to 3D Open
Given the growing need for automatic 3D content creation pipelines, various 3D representations have been studied to generate 3D objects from a single image. Due to its superior rendering efficiency, 3D Gaussian splatting-based models have …