ICLR 2024 accepted papers on Probabilistic and scientific modeling

Molecules and proteins · 44 papers

• SaProt: Protein Language Modeling with Structure-aware Vocabulary (252 citations)
• DNABERT-2: Efficient Foundation Model and Benchmark For Multi-Species Genomes (173 citations)
• CellPLM: Pre-training of Cell Language Model Beyond Single Cells (75 citations)
• Deep Confident Steps to New Pockets: Strategies for Docking Generalization (28 citations)
• SE(3)-Stochastic Flow Matching for Protein Backbone Generation (15 citations)
• MAPE-PPI: Towards Effective and Efficient Protein-Protein Interaction Prediction via Microenvironment-Aware Protein Embedding (10 citations)
• Str2Str: A Score-based Framework for Zero-shot Protein Conformation Sampling (10 citations)
• DecompOpt: Controllable and Decomposed Diffusion Models for Structure-based Molecular Optimization (9 citations)
• From Zero to Turbulence: Generative Modeling for 3D Flow Simulation (7 citations)
• Evaluating Representation Learning on the Protein Structure Universe (6 citations)
• AirPhyNet: Harnessing Physics-Guided Neural Networks for Air Quality Prediction (5 citations)
• Rigid Protein-Protein Docking via Equivariant Elliptic-Paraboloid Interface Prediction (5 citations)

and 32 more in the interactive map.

Variational and generative sampling · 42 papers

• Flow Matching on General Geometries (5 citations)
• Protein Discovery with Discrete Walk-Jump Sampling (5 citations)
• Analysis of Learning a Flow-based Generative Model from Limited Sample Complexity (4 citations)
• Idempotent Generative Network (4 citations)
• Beyond Vanilla Variational Autoencoders: Detecting Posterior Collapse in Conditional and Hierarchical Variational Autoencoders (2 citations)
• Cauchy-Schwarz Divergence Information Bottleneck for Regression (2 citations)
• PhyloGFN: Phylogenetic inference with generative flow networks (2 citations)
• Variational Inference for SDEs Driven by Fractional Noise (2 citations)
• DiffEnc: Variational Diffusion with a Learned Encoder (1 citation)
• Fast and unified path gradient estimators for normalizing flows (1 citation)
• Lifting Architectural Constraints of Injective Flows (1 citation)
• MINDE: Mutual Information Neural Diffusion Estimation (1 citation)

and 30 more in the interactive map.

Dynamical systems · 32 papers

• BrainLM: A foundation model for brain activity recordings (45 citations)
• ODEFormer: Symbolic Regression of Dynamical Systems with Transformers (6 citations)
• A differentiable brain simulator bridging brain simulation and brain-inspired computing (4 citations)
• Hybrid Internal Model: Learning Agile Legged Locomotion with Simulated Robot Response (4 citations)
• Compositional Generative Inverse Design (2 citations)
• DIFFTACTILE: A Physics-based Differentiable Tactile Simulator for Contact-rich Robotic Manipulation (2 citations)
• Multi-modal Gaussian Process Variational Autoencoders for Neural and Behavioral Data (2 citations)
• One-hot Generalized Linear Model for Switching Brain State Discovery (2 citations)
• Course Correcting Koopman Representations (1 citation)
• Implicit Gaussian process representation of vector fields over arbitrary latent manifolds (1 citation)
• Learning Flexible Body Collision Dynamics with Hierarchical Contact Mesh Transformer (1 citation)
• Learning invariant representations of time-homogeneous stochastic dynamical systems (1 citation)

and 20 more in the interactive map.

Differential equations and PDEs · 19 papers

• PINNsFormer: A Transformer-Based Framework For Physics-Informed Neural Networks (27 citations)
• An operator preconditioning perspective on training in physics-informed machine learning (5 citations)
• Scaling physics-informed hard constraints with mixture-of-experts (3 citations)
• ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEs (2 citations)
• Neural Spectral Methods: Self-supervised learning in the spectral domain (2 citations)
• On Accelerating Diffusion-Based Sampling Processes via Improved Integration Approximation (2 citations)
• Symmetric Basis Convolutions for Learning Lagrangian Fluid Mechanics (2 citations)
• Better Neural PDE Solvers Through Data-Free Mesh Movers (1 citation)
• SineNet: Learning Temporal Dynamics in Time-Dependent Partial Differential Equations (1 citation)
• Solving High Frequency and Multi-Scale PDEs with Gaussian Processes (1 citation)
• Accelerating Data Generation for Neural Operators via Krylov Subspace Recycling
• BENO: Boundary-embedded Neural Operators for Elliptic PDEs

and 7 more in the interactive map.

Causal discovery · 18 papers

• Multi-View Causal Representation Learning with Partial Observability (6 citations)
• Gene Regulatory Network Inference in the Presence of Dropouts: a Causal View (2 citations)
• Identifying Representations for Intervention Extrapolation (2 citations)
• A Versatile Causal Discovery Framework to Allow Causally-Related Hidden Variables (1 citation)
• Causal Inference with Conditional Front-Door Adjustment and Identifiable Variational Autoencoder (1 citation)
• CausalTime: Realistically Generated Time-series for Benchmarking of Causal Discovery (1 citation)
• Identifiable Latent Polynomial Causal Models through the Lens of Change (1 citation)
• Object centric architectures enable efficient causal representation learning (1 citation)
• A Dynamical View of the Question of Why
• Causal-StoNet: Causal Inference for High-Dimensional Complex Data
• Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning
• Interventional Fairness on Partially Known Causal Graphs: A Constrained Optimization Approach

and 6 more in the interactive map.

Uncertainty and Gaussian processes · 17 papers

• Variational Bayesian Last Layers (6 citations)
• RECOMBINER: Robust and Enhanced Compression with Bayesian Implicit Neural Representations (2 citations)
• Training Bayesian Neural Networks with Sparse Subspace Variational Inference (2 citations)
• A Symmetry-Aware Exploration of Bayesian Neural Network Posteriors (1 citation)
• On the Posterior Distribution in Denoising: Application to Uncertainty Quantification (1 citation)
• A Hierarchical Bayesian Model for Few-Shot Meta Learning
• Beyond IID weights: sparse and low-rank deep Neural Networks are also Gaussian Processes
• Enhancing Transfer Learning with Flexible Nonparametric Posterior Sampling
• Fast Ensembling with Diffusion Schrödinger Bridge
• Functional Bayesian Tucker Decomposition for Continuous-indexed Tensor Data
• Implicit Maximum a Posteriori Filtering via Adaptive Optimization
• In-Context Learning through the Bayesian Prism

and 5 more in the interactive map.

Treatment effects · 16 papers

• Debiased Collaborative Filtering with Kernel-Based Causal Balancing (7 citations)
• Independent-Set Design of Experiments for Estimating Treatment and Spillover Effects under Network Interference (3 citations)
• Bounds on Representation-Induced Confounding Bias for Treatment Effect Estimation (2 citations)
• A Neural Framework for Generalized Causal Sensitivity Analysis (1 citation)
• Adaptive Instrument Design for Indirect Experiments
• Bayesian Neural Controlled Differential Equations for Treatment Effect Estimation
• Be Aware of the Neighborhood Effect: Modeling Selection Bias under Interference
• Conditional Instrumental Variable Regression with Representation Learning for Causal Inference
• Defining Expertise: Applications to Treatment Effect Estimation
• Doubly Robust Proximal Causal Learning for Continuous Treatments
• Empirical Analysis of Model Selection for Heterogeneous Causal Effect Estimation
• ODE Discovery for Longitudinal Heterogeneous Treatment Effects Inference

and 4 more in the interactive map.

Bayesian optimization · 8 papers

• A Study of Bayesian Neural Network Surrogates for Bayesian Optimization (5 citations)
• A General Framework for User-Guided Bayesian Optimization (2 citations)
• Adversarial Causal Bayesian Optimization (2 citations)
• SYMBOL: Generating Flexible Black-Box Optimizers through Symbolic Equation Learning (1 citation)
• Bayesian Optimization through Gaussian Cox Process Models for Spatio-temporal Data
• Making RL with Preference-based Feedback Efficient via Randomization
• A Unified Framework for Bayesian Optimization under Contextual Uncertainty
• Meta-VBO: Utilizing Prior Tasks in Optimizing Risk Measures with Gaussian Processes