828 citations · 5.6k across the 171 of their papers we have counts for
18 papers · 1 filter
Flow Map Distillation Without Data
Shangyuan Tong, Nanye Ma, Saining Xie +1
State-of-the-art flow models achieve remarkable quality but require slow, iterative sampling. To accelerate this, flow maps can be distilled from pre-trained teachers, a procedure…
HarnessLLM: Automatic Testing Harness Generation via Reinforcement Learning
Yujian Liu, Jiabao Ji, Yang Zhang +3
Existing LLM-based automatic test generation methods mainly produce input and expected output pairs to categorize the intended behavior of correct programs. Although straightforwar…
Next Semantic Scale Prediction via Hierarchical Diffusion Language Models
Cai Zhou, Chenyu Wang, Dinghuai Zhang +4
In this paper we introduce Hierarchical Diffusion Language Models (HDLM) -- a novel family of discrete diffusion models for language modeling. HDLM builds on a hierarchical vocabul…
SPG: Sandwiched Policy Gradient for Masked Diffusion Language Models
Chenyu Wang, Paria Rashidinejad, DiJia Su +9
Diffusion large language models (dLLMs) are emerging as an efficient alternative to autoregressive models due to their ability to decode multiple tokens in parallel. However, align…
Coevolutionary Continuous Discrete Diffusion: Make Your Diffusion Language Model a Latent Reasoner
Cai Zhou, Chenxiao Yang, Yi Hu +7
Diffusion language models, especially masked discrete diffusion models, have achieved great success recently. While there are some theoretical and primary empirical results showing…
Implicit Augmentation from Distributional Symmetry in Turbulence Super-Resolution
Julia Balla, Jeremiah Bailey, Ali Backour +4
The immense computational cost of simulating turbulence has motivated the use of machine learning approaches for super-resolving turbulent flows. A central challenge is ensuring th…
AI-based Methods for Simulating, Sampling, and Predicting Protein Ensembles
Bowen Jing, Bonnie Berger, Tommi Jaakkola
Advances in deep learning have opened an era of abundant and accurate predicted protein structures; however, similar progress in protein ensembles has remained elusive. This review…
GLASS Flows: Transition Sampling for Alignment of Flow and Diffusion Models
Peter Holderrieth, Uriel Singer, Tommi Jaakkola +3
The performance of flow matching and diffusion models can be greatly improved at inference time using reward alignment algorithms, yet efficiency remains a major limitation. While…
Continuously Tempered Diffusion Samplers
Ezra Erives, Bowen Jing, Peter Holderrieth +1
Annealing-based neural samplers seek to amortize sampling from unnormalized distributions by training neural networks to transport a family of densities interpolating from source t…
Pi-SAGE: Permutation-invariant surface-aware graph encoder for binding affinity prediction
Sharmi Banerjee, Mostafa Karimi, Melih Yilmaz +4
Protein surface fingerprint encodes chemical and geometric features that govern protein-protein interactions and can be used to predict changes in binding affinity between two prot…
Learning Diffusion Models with Flexible Representation Guidance
Chenyu Wang, Cai Zhou, Sharut Gupta +4
Diffusion models can be improved with additional guidance towards more effective representations of input. Indeed, prior empirical work has already shown that aligning internal rep…
ProxelGen: Generating Proteins as 3D Densities
Felix Faltings, Hannes Stark, Regina Barzilay +1
We develop ProxelGen, a protein structure generative model that operates on 3D densities as opposed to the prevailing 3D point cloud representations. Representing proteins as voxel…
Thought calibration: Efficient and confident test-time scaling
Menghua Wu, Cai Zhou, Stephen Bates +1
Reasoning large language models achieve impressive test-time scaling by thinking for longer, but this performance gain comes at significant compute cost. Directly limiting test-tim…
Protein FID: Improved Evaluation of Protein Structure Generative Models
Felix Faltings, Hannes Stark, Tommi Jaakkola +1
Protein structure generative models have seen a recent surge of interest, but meaningfully evaluating them computationally is an active area of research. While current metrics have…
Hierarchical protein backbone generation with latent and structure diffusion
Jason Yim, Marouane Jaakik, Ge Liu +5
We propose a hierarchical protein backbone generative model that separates coarse and fine-grained details. Our approach called LSD consists of two stages: sampling latents which a…
ProtComposer: Compositional Protein Structure Generation with 3D Ellipsoids
Hannes Stark, Bowen Jing, Tomas Geffner +4
We develop ProtComposer to generate protein structures conditioned on spatial protein layouts that are specified via a set of 3D ellipsoids capturing substructure shapes and semant…
LEAPS: A discrete neural sampler via locally equivariant networks
Peter Holderrieth, Michael S. Albergo, Tommi Jaakkola
We propose "LEAPS", an algorithm to sample from discrete distributions known up to normalization by learning a rate matrix of a continuous-time Markov chain (CTMC). LEAPS can be se…
Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps
Nanye Ma, Shangyuan Tong, Haolin Jia +8
Generative models have made significant impacts across various domains, largely due to their ability to scale during training by increasing data, computational resources, and model…