ICLR 2025PastOther
Learning Meaningful Representations of Life (LMRL) Workshop at ICLR 2025
ICLR 2025 Workshop LMRL
- Submission deadline
- Feb 13, 2025, 11:59 UTCimported from OpenReview — check the website for extensions
- Submission portal
- OpenReview
- Notes
- Topics were auto-suggested and may be imprecise — edits welcome.
Accepted papers (84)
Fetched from OpenReview (v2) on 2026-06-10.
2DE: a probabilistic method for differential expression across niches in spatial transcriptomics data
A pretrained SCVI model for 60,000 drug perturbation experiments in 100 million cells
Adaptive Discrete Tokenization of Electrocardiograms for Clinical Applications
AI Foundation Models for Personalized Health Monitoring: Learning Meaningful Representations of Metabolic Profiles
AI-Powered Virtual Tissues from Spatial Proteomics for Clinical Diagnostics and Biomedical Discovery
Benchmarking and optimizing organism wide single-cell RNA alignment methods
Benchmarking Sample Representations from Single-Cell Data: Metrics for Biologically Meaningful Embeddings
Beyond Schrödinger Bridges: A Least-Squares Approach for Learning Stochastic Dynamics with Unknown Volatility
Boosting Protein Graph Representations through Static-Dynamic Fusion
Bridging scales between chemical space and behavioral phenotype
Bridging Sequence and Kinetics: Utilizing Multi-scale Representations for Genome-Scale Metabolic Models
CardioPRIME: Cardiovascular Physiological Representation Integration With Multimodal Embeddings
CellCLIP - Learning Perturbation Effects in Cell Painting via Text-Guided Contrastive Learning
Cellular-Guided Graph Generative Model
Character-level Tokenizations as Powerful Inductive Biases for RNA Foundational Models
Curly Flow Matching for Learning Non-gradient Field Dynamics
Decision Tree Induction with Dynamic Feature Generation: A Framework for Interpretable DNA Sequence Analysis
Delta ECG: A Genetic Perspective
DiffGraphTrans: A Differential Attention-Based Approach for Extracting Meaningful Features of Drug Combinations
END-TO-END INTERPRETABLE GRAPH LEARNING FOR PATIENT CLASSIFICATION
Exploring Query-to-reference Mapping Challenges for Automated Single-Cell Atlas-based Diagnostics
Extending Prot2Token: Aligning Protein Language Models for Unified and Diverse Protein Prediction Tasks
Flexible Models of Functional Annotations to Variant Effects using Accelerated Linear Algebra
Fractional Brownian Bridges for Aligned Data
From Mechanistic Interpretability to Mechanistic Biology: Training, Evaluating, and Interpreting Sparse Autoencoders on Protein Language Models
From Medical Literature to Predictive Features: An Evidence-based Knowledge Graph Approach
Generalized Representation Learning for Multimodal Histology Imaging Data Through Vision-Language Modeling
GluFormer: Learning Generalizable Representations from Continuous Glucose Monitoring Data
GRASP: GRAph-Structured Pyramidal Whole Slide Image Representation
Guided Generation of B-cell Receptors with Conditional Walk-Jump Sampling
Hierarchical Mixture of Topological Experts for Molecular Property Prediction
Identifying Critical Phases for Disease Onset with Sparse Haematological Biomarkers
Implicit Neural Representations of Molecular Vector-Valued Functions
Integrating Protein Language Model and Active Learning for Few-Shot Viral Variant Detection
Interpretable Enzyme Function Prediction via Residue-Level Detection
Interpretable Self-Supervised Prototype Learning for Single-Cell Transcriptomics
Interpreting and Steering Protein Language Models through Sparse Autoencoders
Large Language Model is Secretly a Protein Sequence Optimizer
Latent Representation Encoding and Multimodal Biomarkers for Post-Stroke Speech Assessment
Learning a mechanical growth model of flower morphogenesis
Learning to Predict Ensembles of Protein Conformations from Molecular Dynamics Simulation Trajectories
Leveraging State Space Models in Long Range Genomics
Leveraging Transfer Learning and Multimodal Foundation Models for Antibiotic Discovery Against Data-Scarce Escherichia coli Strains
Ligand-Conditioned Binding Site Prediction Using Contrastive Geometric Learning
MeMDLM: De Novo Membrane Protein Design with Property-Guided Discrete Diffusion
Metabolically Constrained Neural Networks for Bioprocess Optimization
Metalorian: De Novo Generation of Heavy Metal-Binding Peptides with Classifier-Guided Diffusion Sampling
MODIS: Multi-Omics Data Integration for small and unpaired datasets
moPPIt: De Novo Generation of Motif-Specific Peptide Binders via Conditional Uniform Discrete Diffusion
Multi-Modal Disentanglement of Spatial Transcriptomics and Histopathology Imaging
Multi-Modal Representation learning for molecules
muPPIt: De Novo Generation of Mutant-Specific Peptide Binders via Conditional Uniform Discrete Diffusion
Mutagenic: An Embedding-Based Approach to Protein Masking for Functional Redesign
NOLAN: CONSTRUCTING GRAPH REPRESENTATION OF TISSUE STRUCTURE WITH SELF-SUPERVISED LEARNING
Non-invasive, label-free biochemical imaging of intact cerebral organoids via deep learning-enhanced Raman microspectroscopy
Omni-Mol: Exploring Universal Convergent Space for Omni-Molecular Tasks
On multi-scale Graph Representation Learning
Out-of-distribution evaluations of channel agnostic masked autoencoders in fluorescence microscopy
PETIMOT: A Novel Framework for Inferring Protein Motions from Sparse Data Using SE(3)-Equivariant Graph Neural Networks
Phyla: Towards A Foundation Model For Phylogenetic Inference
Protriever: End-to-End Differentiable Protein Homology Search for Fitness Prediction
Representation Learning for Distributional Perturbation Extrapolation
Roll-AE: A Spatiotemporal Invariant Autoencoder for Uncovering Neuronal Electrophysiological Patterns
RxRx3-core: Benchmarking drug-target interactions in high-content microscopy
Sampling Protein Language Models for Functional Protein Design
Self-supervised Learning for Encoding Between-Subject Information in Clinical EEG
Simulation-Free Structure Learning For Stochastic Dynamics
SOAPI: Siamese-guided generation of Off-Target-Avoiding Protein Interactions
Spatially-Informed Sampling Enables Accurate Prediction of Large-Scale Mutational Effects
STATE-SPACE-LIKE MODELS TO CALL COPY NUMBERS
Target localization in cell-based image analysis and disease diagnosis
Task-Driven Graph Neural Network Pre-Training: A Path to Robust EEG Representations in Motor Planning
Tensor-DTI: Enhancing Biomolecular Interaction Prediction with Contrastive Embedding Learning
To Bin or not to Bin: Alternative Representations of Mass Spectra
Towards Interpretable Protein Structure Prediction with Sparse Autoencoders
Towards Protein Sequence & Structure Co-Design with Multi-Modal Language Models
Towards Representation Learning for Phenotyping beyond Animal Pose Estimation
Transformer-Based Integrative Patient Representations from Single-Cell RNA Data
Transformers trained on proteins can learn to attend to Euclidean distance
Universally Applicable And Tunable Graph-Based Coarse-Graining For Machine Learning Force Fields
Unsupervised Deep Disentangled Representation of Single-Cell Omics with DRVI
Unsupervised Whole-Genome Representation Learning Captures Bacterial Phenotypes
Using Autoregressive-Transformer Model for Protein-Ligand Binding Site Prediction
Weakly Supervised Latent Variable Inference of Proximity Bias in CRISPR Gene Knockouts from Single-Cell Images