{"id":186,"date":"2025-04-15T12:14:20","date_gmt":"2025-04-15T12:14:20","guid":{"rendered":"https:\/\/valancelabs.digitalhero.uk.com\/?page_id=186"},"modified":"2025-05-20T11:37:26","modified_gmt":"2025-05-20T11:37:26","slug":"research","status":"publish","type":"page","link":"https:\/\/www.valencelabs.com\/fr\/research\/","title":{"rendered":"Publications"},"content":{"rendered":"
\n \"Page\n<\/div>\n
\n \"Publication\n<\/div>\n
\n
\n
\n Recherche <\/div>\n

\n Publications
\n \/ 68 <\/div>\n <\/h1>\n <\/div>\n
\n
\n
All<\/div>\n <\/div>\n\n
\n \n
\n
\n May 20th, 2025 <\/div>\n
\n
Virtual Cells: Predict, Explain, Discover<\/h5>\n
\n Drug discovery is fundamentally a process of inferring the effects of treatments on patients, and would therefore benefit immensely from computational models that can reliably simulate patient responses, enabling researc… <\/div>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n May 14th, 2025 <\/div>\n
\n
TxPert: Leveraging Biochemical Relationships for Out-of-Distribution Transcriptomic Perturbation Prediction<\/h5>\n
\n Accurately predicting cellular responses to genetic perturbations is essential for understanding disease mechanisms and designing effective therapies. Yet exhaustively exploring the space of possible perturbations (e.g.,… <\/div>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n April 23rd, 2025 <\/div>\n
\n
Scaling Deep Learning Solutions for Transition Path Sampling<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n April 18th, 2025 <\/div>\n
\n
Weakly Supervised Latent Variable Inference of Proximity Bias in CRISPR Gene Knockouts from Single-Cell Images<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n April 14th, 2025 <\/div>\n
\n
Adaptive teachers for amortized samplers<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n April 11th, 2025 <\/div>\n
\n
Efficient Biological Data Acquisition through Inference Set Design<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n April 9th, 2025 <\/div>\n
\n
SynFlowNet: Design of Diverse and Novel Molecules with Synthesis Constraints<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n March 1st, 2025 <\/div>\n
\n
Towards Improving Exploration through Sibling Augmented GFlowNets<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n February 12th, 2025 <\/div>\n
\n
Random Policy Evaluation for Recovering Policies of Generative Flow Networks<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n February 11th, 2025 <\/div>\n
\n
Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n February 5th, 2025 <\/div>\n
\n
Learning Symmetries Through Loss Landscape<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n February 1st, 2025 <\/div>\n
\n
Gaussian Process Simplicial Complex Prediction via the Ricci-Hodgelet Representations<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n December 8th, 2024 <\/div>\n
\n
Implicit Delta Learning of High Fidelity Neural Network Potentials<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n November 4th, 2024 <\/div>\n
\n
ViTally Consistent: Scaling Biological Representation Learning for Cell Microscopy<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n November 1st, 2024 <\/div>\n
\n
QGFN: Controllable Greediness with Action Values<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n October 29th, 2024 <\/div>\n
\n
ET-Flow: Equivariant Flow-Matching for Molecular Conformer Generation<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n October 26th, 2024 <\/div>\n
\n
SAFE setup for generative molecular design<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n October 19th, 2024 <\/div>\n
\n
Action abstractions for amortized sampling<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n October 17th, 2024 <\/div>\n
\n
Benchmarking Transcriptomics Foundation Models for Perturbation Analysis : one PCA still rules them all<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n October 14th, 2024 <\/div>\n
\n
Graph Classification Gaussian Processes via Hodgelet Spectral Features<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n October 8th, 2024 <\/div>\n
\n
Batched Bayesian optimization with correlated candidate uncertainties<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n October 6th, 2024 <\/div>\n
\n
Improved Off-policy Reinforcement Learning in Biological Sequence Design<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n October 4th, 2024 <\/div>\n
\n
A call for an industry-led initiative to critically assess machine learning for real-world drug discovery<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n September 11th, 2024 <\/div>\n
\n
On the Scalability of GNNs for Molecular Graphs<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n September 11th, 2024 <\/div>\n
\n
Automated Discovery of Pairwise Interactions from Unstructured Data<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n September 10th, 2024 <\/div>\n
\n
How Molecules Impact Cells: Unlocking Contrastive PhenoMolecular Retrieval<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n June 10th, 2024 <\/div>\n
\n
Graph Positional and Structural Encoder<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n June 2nd, 2024 <\/div>\n
\n
Learning to Scale Logits for Temperature-Conditional GFlowNets<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n May 31st, 2024 <\/div>\n
\n
Amortizing intractable inference in diffusion models for vision, language, and control<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n April 2nd, 2024 <\/div>\n
\n
Propensity Score Alignment for Unpaired Multimodal Data<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n March 30th, 2024 <\/div>\n
\n
Targeted Sequential Indirect Experiment Design<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n March 27th, 2024 <\/div>\n
\n
Discrete Probabilistic Inference as Control in Multi-path Environments<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n November 6th, 2023 <\/div>\n
\n
DGFN: Double Generative Flow Networks<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n November 2nd, 2023 <\/div>\n
\n
Generating QM1B with PySCFipu<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n October 30th, 2023 <\/div>\n
\n
Role of Structural and Conformational Diversity for Machine Learning Potentials<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n October 27th, 2023 <\/div>\n
\n
Latent Space Simulator for Unveiling Molecular Free Energy Landscapes and Predicting Transition Dynamics<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n October 18th, 2023 <\/div>\n
\n
Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasets<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n October 16th, 2023 <\/div>\n
\n
Gotta be SAFE: A New Framework for Molecular Design<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n July 14th, 2023 <\/div>\n
\n
Graph Positional and Structural Encoder<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n June 7th, 2023 <\/div>\n
\n
Goal-conditioned GFlowNets for Controllable Multi-Objective Molecular Design<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n June 5th, 2023 <\/div>\n
\n
Real-World Molecular Out-Of-Distribution: Specification and Investigation<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n May 26th, 2023 <\/div>\n
\n
UNSAT Solver Synthesis via Monte Carlo Forest Search<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n May 11th, 2023 <\/div>\n
\n
Towards Understanding and Improving GFlowNet Training<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n March 6th, 2023 <\/div>\n
\n
MoDTI: Modular Framework For Evaluating Inductive Biases in DTI Modeling<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n March 6th, 2023 <\/div>\n
\n
Task-Agnostic Graph Neural Network Evaluation via Adversarial Collaboration<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n February 11th, 2023 <\/div>\n
\n
Sequential Underspecified Instrument Selection for Cause-Effect Estimation<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n February 9th, 2023 <\/div>\n
\n
Helixer\u2013de novo Prediction of Primary Eukaryotic Gene Models Combining Deep Learning and a Hidden Markov Model<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n February 8th, 2023 <\/div>\n
\n
DynGFN: Bayesian Dynamic Causal Discovery Using Generative Flow Networks<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n February 1st, 2023 <\/div>\n
\n
GFlowNets for AI-driven Scientific Discovery<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n November 7th, 2022 <\/div>\n
\n
Object-centric Causal Representation Learning<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n October 29th, 2022 <\/div>\n
\n
Object-centric architectures enable efficient causal representation learning<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n October 23rd, 2022 <\/div>\n
\n
Multi-Objective GFlowNets<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n September 26th, 2022 <\/div>\n
\n
Learning GFlowNets From Partial Episodes for Improved Convergence and Stability<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n July 9th, 2022 <\/div>\n
\n
Leveraging Structure Between Environments: Phylogenetic Regularization Incentivizes Disentangled Representations<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n June 16th, 2022 <\/div>\n
\n
Long Range Graph Benchmark<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n June 2nd, 2022 <\/div>\n
\n
Weakly Supervised Representation Learning with Sparse Perturbations<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n May 25th, 2022 <\/div>\n
\n
Recipe for a General, Powerful, Scalable Graph Transformer<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n October 29th, 2021 <\/div>\n
\n
Properties From Mechanisms: an Equivariance Perspective on Identifiable Representation Learning<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n October 8th, 2021 <\/div>\n
\n
3D Infomax improves GNNs for Molecular Property Prediction<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n October 4th, 2021 <\/div>\n
\n
On the Robustness of Generalization of Drug\u2013Drug Interaction Models<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n June 7th, 2021 <\/div>\n
\n
Rethinking Graph Transformers with Spectral Attention<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n December 16th, 2020 <\/div>\n
\n
Helixer: Cross-species Gene Annotation of Large Eukaryotic Genomes Using Deep Learning<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n December 15th, 2020 <\/div>\n
\n
Molecular Design in Synthetically Accessible Chemical Space via Deep Reinforcement Learning<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n October 6th, 2020 <\/div>\n
\n
Directional Graph Networks<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n May 16th, 2020 <\/div>\n
\n
Geodesics in Fibered Latent Spaces: A Geometric Approach to Learning Correspondences Between Conditions<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n April 12th, 2020 <\/div>\n
\n
Principal Neighbourhood Aggregation for Graph Nets<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n May 28th, 2019 <\/div>\n
\n
Towards Interpretable Sparse Graph Representation Learning with Laplacian Pooling<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n \n
\n
\n May 28th, 2019 <\/div>\n
\n
Adaptive Deep Kernel Learning<\/h5>\n <\/div>\n
\n \n \n <\/svg>\n <\/div>\n <\/div>\n <\/a>\n <\/div>\n <\/div>\n<\/div>","protected":false},"excerpt":{"rendered":"","protected":false},"author":3,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-186","page","type-page","status-publish","hentry"],"yoast_head":"\nValence Labs | Publications<\/title>\n\n\n\n\n\n\n\n\n\n\t\n\t\n\t\n\n