OmniMatBench: A Human-Calibrated Multimodal Reasoning Benchmark Across 19 Materials Science Subfields Paper • 2605.29833 • Published May 29
Eigenbasis-Independent Learnable Spectral Positional Encodings for Directed Graphs via Hermitian Block Krylov Subspaces Paper • 2607.07032 • Published Jul 11
Reachability Is Not Realization: Tracing the Sources of LLM Benchmark Gains Paper • 2608.03219 • Published Aug 4
Equivariant Neural Primal-Dual Assignment for Maximum Common Edge Subgraphs Paper • 2609.32661 • Published 17 days ago
$\text{GSF-}χ$: Global Stereochemical Fields for Chiral Graph Transformers Paper • 2609.12532 • Published Sep 11 • 1
Benchmarking Positional Encodings for GNNs and Graph Transformers Paper • 2411.12732 • Published Nov 19, 2024 • 1
DeepResearch Arena: The First Exam of LLMs' Research Abilities via Seminar-Grounded Tasks Paper • 2509.01396 • Published Sep 1, 2025 • 59
MolSpectLLM: A Molecular Foundation Model Bridging Spectroscopy, Molecule Elucidation, and 3D Structure Generation Paper • 2509.21861 • Published Sep 26, 2025 • 2
QCBench: Evaluating Large Language Models on Domain-Specific Quantitative Chemistry Paper • 2508.01670 • Published Aug 3, 2025
MolAct: An Agentic RL Framework for Molecular Editing and Property Optimization Paper • 2512.20135 • Published Dec 23, 2025
NMRGym: A Comprehensive Benchmark for Nuclear Magnetic Resonance Based Molecular Structure Elucidation Paper • 2601.15763 • Published Jan 22 • 1
PolyReal: A Benchmark for Real-World Polymer Science Workflows Paper • 2604.02934 • Published Apr 3 • 2
DeepProtein: Deep Learning Library and Benchmark for Protein Sequence Learning Paper • 2410.02023 • Published Apr 6, 2025 • 1