Lessons Learned: A Multi-Agent Framework for Code LLMs to Learn and ImproveYuanzhe LiuRyan Denget al.2025NeurIPS 2025
Causal LLM Routing: End-to-End Regret Minimization from Observational DataAsterios TsiourvasWei Sunet al.2025NeurIPS 2025
Latent Principle Discovery for Language Model Self-ImprovementKeshav RamjiTahira Naseemet al.2025NeurIPS 2025
FlowState: Sampling-Rate Invariant Time Series Foundation Model with Dynamic Forecasting HorizonsLars GrafThomas Bohnstinglet al.2025NeurIPS 2025
MermaidSeqBench: An Evaluation Benchmark for LLM-to-Mermaid Sequence Diagram GenerationBasel ShbitaFarhan Ahmedet al.2025NeurIPS 2025
Automated Structure Elucidation at Human-Level Accuracy via a Multimodal Multitask Language ModelMarvin AlbertsNina Hartrampfet al.2025NeurIPS 2025
Foundation Models Enabling Multi-Scale Battery Materials Discovery: From Molecules To DevicesVidushi SharmaAndy Teket al.2025NeurIPS 2025
Toward a Coherent Virtual Cell Model: Probing Biological World-Model Coherence in Transcriptomic Foundation ModelsNoa MorielYishai Shimoniet al.2025NeurIPS 2025
Emergent Pose-Invariance in 3D Molecular Representations via Multimodal LearningEduardo Almeida SoaresVictor Yukio Shirasunaet al.2025NeurIPS 2025
Token-Level Early Fusion Model Bridging Text and 3D Electron Density Grids in ChemistryEduardo Almeida SoaresEmilio Ashton Vital Brazilet al.2025NeurIPS 2025