← Back to feed

Mechanistic Reaction Prediction via Discrete Flow Matching on Graph-Structured Electron Occupation

L5 · ResearcherResearcharXiv· 8/27/2026

Presents a fundamentally new approach to reaction prediction with mechanistic interpretability and strong OOD performance.

AI Summary

Researchers introduce MAELLE, a novel AI approach that models chemical reactions as discrete flow matching over electron occupation vectors rather than molecular topology.

Excerpt

Chemical reactions are fundamentally transformations in electron space, yet most machine learning approaches model them either through \textit{de novo} generation of product molecules or through heuristic graph edits that operate directly on molecular topology. We introduce MAELLE (\textbf{M}ech\textbf{A}nistic \textbf{E}dit f\textbf{L}ow-matching on e\textbf{L}ectron r\textbf{E}arrangements), which instead models reactions as discrete flow matching over electron occupation vectors. Concretely,

Read Original
0 upvotes · 0 downvotes · 1 min read

Related Articles

L4 · DeveloperResearcharXiv
Persona-Execution Separation: An Architecture Pattern for Evolving LLM Agents under Execution Audit

Presents Persona-Execution Separation, an architecture pattern for enterprise LLM agents that keeps execution auditable while allowing persona instructions to evolve freely.

L5 · ResearcherResearcharXiv
LLMs Can Design Near-Optimal OR Algorithms

GPT-5.6 can design near-optimal algorithms for operations research problems like inventory control and queueing networks, matching or beating specialized methods with minimal human input.

L5 · ResearcherResearcharXiv
Scaling Graph Neural Networks for Friend Recommendation: Multi-Hash User Embeddings and Temporal Neighbor Sampling

Researchers present a scalable GNN system for friend recommendation that reduces embedding table size by 98% and improves temporal sampling efficiency, achieving 16% more friend additions in production tests.

L5 · ResearcherResearcharXiv
From Static to Dynamic: Benchmarking Real-World Code Review with MCR-Bench

Researchers introduce MCR-Bench, the first defect state-aware benchmark for multi-round code review, evaluating LLMs' limitations in iterative defect detection and tracking.

L5 · ResearcherResearcharXiv
TTPO: Test-Time Policy Optimization

Researchers propose TTPO, a novel test-time policy optimization method that enhances large language models' mathematical reasoning without ground-truth labels.