Lu Chen

LigBench transforms the landscape of LLM-driven research idea generation by providing a unified benchmark that aligns closely with expert evaluations.

JAPE reveals that modeling evolving dependency structures can significantly enhance anomaly prediction accuracy and explainability in multivariate time series.

Achieving 93.02% accuracy in molecular structure recognition, MinerU.Chem outperforms existing systems, unlocking new possibilities for AI-driven chemistry research.

OrthoPilot outperformed seasoned orthopaedic experts in diagnostic reasoning, achieving a 10.6% increase in management success for complex musculoskeletal cases.

Uncertainty-guided sensing can reduce channel knowledge prediction errors by over 40% while adapting to new environments with minimal data.

Claim drift in automated research can lead to significant discrepancies, but Xcientist ensures that every generated mechanism remains accountable and traceable back to its evidential roots.

MiniMax-M2 proves that massive parameter counts don't always translate to better agentic performance; strategic activation of a smaller subset can unlock frontier-level intelligence.

LLMs maintain surface syntax but collapse on structural semantics, revealing critical gaps in their ability to function as reliable agents in complex environments.

Despite the promise of transcriptomic models for predicting immunotherapy response, existing models fail to generalize across independent patient cohorts, raising serious questions about their clinical utility.

Forget quadratic attention: FEAT achieves state-of-the-art performance on structured data with linear complexity and 40x faster inference.

LLMs still struggle to answer questions about AI research papers, as evidenced by a new challenging dataset, AirQA, which also comes with an automated method for synthesizing training data to improve performance.