MermaidSeqBench: An Evaluation Benchmark for LLM-to-Mermaid Sequence Diagram GenerationBasel ShbitaFarhan Ahmedet al.2025NeurIPS 2025Workshop paper
Uncertainty-Aware Prediction of Climate Extremes Using Fine-Tuned Time-Series Foundation ModelsImran NasimJoao Lucas de Sousa Almeida2025NeurIPS 2025Workshop paper
STRIDE: A Systematic Framework for Selecting AI Modalities—Agentic AI, AI Assistants, or LLM CallsShubhi AsthanaRuchi Mahindruet al.2025NeurIPS 2025Workshop paper
Foundation Models Enabling Multi-Scale Battery Materials Discovery: From Molecules To DevicesVidushi SharmaAndy Teket al.2025NeurIPS 2025Workshop paper
ConstrainedSQL: Training LLMs for Text2SQL via Constrained Reinforcement LearningWeiqin ChenNhan Phamet al.2025NeurIPS 2025Workshop paper
Verifiable Chemical Reasoning through Tool-Calling Agentic WorkflowGabrielle GaudeauShinnosuke Tanakaet al.2025NeurIPS 2025Workshop paper
Quantifying policy uncertainty in generative flow networks with uncertain rewardsRamon Nartallo-kaluarachchiRobert Manson Sawkoet al.2025NeurIPS 2025Workshop paper
A Data-driven ML Approach for Maximizing Performance in LLM-Adapter ServingFerran Agullo LopezJoan Oliveras Torraet al.2025NeurIPS 2025Workshop paper
Carbon-m1: a Massive, Multi-Modal Synthetic Dataset for Complex Polymeric MaterialsNathaniel Park2025NeurIPS 2025Workshop paper
SemCLIP: A Semantic Memory-Aligned Vision Language ModelTanveer Syeda-MahmoodNiharika DSouzaet al.2025NeurIPS 2025Workshop paper