molecular-generation

Tag

Cards List
#molecular-generation

S1-Omni: A Unified Multimodal Reasoning Model for Scientific Understanding, Prediction, and Generation

arXiv cs.AI · 15h ago Cached

S1-Omni is a unified multimodal reasoning model for scientific tasks including understanding, prediction, and generation. It is trained on a corpus of 200 scientific tasks and outperforms GPT-5.5 and Gemini-3.1-Pro on most benchmarks.

0 favorites 0 likes
#molecular-generation

HEDGEHOG: Hierarchical Evaluation of Drug Generators Through Rigorous Filtration

arXiv cs.LG · 4d ago Cached

Introduces HEDGEHOG, a hierarchical benchmark for evaluating molecular generative models in drug discovery, revealing that only 0.65% of generated molecules pass all medicinal chemistry and docking filters.

0 favorites 0 likes
#molecular-generation

SinAE: A Single-Architecture Flow-Matching Autoencoder for Cross-Domain Atomic Systems

arXiv cs.LG · 5d ago Cached

SinAE introduces a single-architecture flow-matching autoencoder using vanilla Transformers that achieves near-lossless reconstruction across molecules, crystals, and proteins, enabling cross-domain training and strong generative performance on standard benchmarks.

0 favorites 0 likes
#molecular-generation

Generating Developable 3D Molecules via Pocket-Conditioned Diffusion and Property-Aware Optimization

arXiv cs.LG · 5d ago Cached

This paper introduces a novel diffusion-based generative model for structure-based drug design that decouples pocket and ligand representation learning and incorporates multi-scale interaction signals and property-aware optimization to generate developable 3D molecules with improved binding affinity and ADMET properties.

0 favorites 0 likes
#molecular-generation

Reward Transport: Property Control in Flow Matching via Noise-Space Alignment

arXiv cs.LG · 2026-07-13 Cached

This paper introduces Reward Transport, a method that uses optimal transport coupling during flow matching training to align a scalar noise coordinate with molecular rewards, enabling monotone control over molecular properties like logP and QED at inference without additional computation.

0 favorites 0 likes
#molecular-generation

DrugGen 2: A disease-aware language model for enhancing drug discovery

Hugging Face Daily Papers · 2026-07-09 Cached

DrugGen-2 fine-tunes GPT-2 using supervised learning and reinforcement learning (GRPO) to generate small molecules conditioned on both disease ontology and target protein sequences, achieving superior diversity and binding affinity for drug discovery.

0 favorites 0 likes
#molecular-generation

MolSafeEval: A Benchmark for Uncovering Safety Risks in AI-Generated Molecules

arXiv cs.LG · 2026-07-02 Cached

Introduces MolSafeEval, a benchmark dedicated to evaluating safety risks in AI-generated molecules by integrating heterogeneous safety knowledge into a molecular safety knowledge graph and leveraging LLM-based reasoning for systematic detection of unsafe features.

0 favorites 0 likes
#molecular-generation

Sesame: Structure-Aware Molecular Generation via Spatial Density-Map Conditioning

arXiv cs.LG · 2026-06-24 Cached

This paper introduces Sesame, a diffusion-based molecular generation model that conditions on partial molecular structure and protein pocket via spatial density maps, enabling both de novo generation and fragment-conditioned lead optimization for drug design.

0 favorites 0 likes
#molecular-generation

Smoothing Dark Areas in Molecular Latent Diffusion

arXiv cs.LG · 2026-06-15 Cached

This paper introduces TopVAE, a topology-optimized VAE that reduces 'dark areas' in molecular latent diffusion by making the decoder internalize structural and chemical constraints, achieving significant improvements in molecular generation quality.

0 favorites 0 likes
#molecular-generation

Controllable Molecular Generative Foundation Models

arXiv cs.LG · 2026-05-18 Cached

Proposes CoMole, a controllable molecular generative foundation model using motif-aware graph diffusion and reinforcement learning, achieving superior controllability across materials and drug discovery benchmarks.

0 favorites 0 likes
#molecular-generation

ToolMol: Evolutionary Agentic Framework for Multi-objective Drug Discovery

arXiv cs.LG · 2026-05-14 Cached

ToolMol is an evolutionary agentic framework that combines a multi-objective genetic algorithm with an LLM-based operator to design small-molecule drugs, achieving state-of-the-art binding affinity and drug-likeness on multiple protein targets.

0 favorites 0 likes
← Back to home

Submit Feedback