PPL
Liang Wang
Papers (7)
ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM InferenceText2CAD-Bench: A Benchmark for LLM-based Text-to-Parametric CAD GenerationMulti-Paradigm Agent Interaction in Practice:A Systematic Analysis of Generator-Evaluator, ReAct Loop,and Adversarial Evaluation in the buddyMe FrameworkReading the Cell, Designing the Cure: Perturbation-Conditioned Molecular Diffusion for Function-Oriented Drug DesignA Unified Knowledge Embedded Reinforcement Learning-based Framework for Generalized Capacitated Vehicle Routing ProblemsArtificial Intelligence-Assistant Cardiotocography: Unified Model for Signal Reconstruction, Fetal Heart Rate Analysis, and Variability AssessmentGood to Go: The LOOP Skill Engine That Hits 99% Success and Slashes Token Usage by 99% via One-Shot Recording and Deterministic Replay