Wei Lin

6 papers ELLIS Unit Linz & LIT AI Lab, JKU

• Bi-Level Decision-Focused Causal Learning for Large-Scale Marketing Optimization: Bridging Observational and Experimental Data
• Data-Juicer 2.0: Cloud-Scale Adaptive Data Processing for and with Foundation Models
• Learning Provably Improves the Convergence of Gradient Descent
• PolarQuant: Leveraging Polar Transformation for Key Cache Quantization and Decoding Acceleration
• STSBench: A Spatio-temporal Scenario Benchmark for Multi-modal Large Language Models in Autonomous Driving
• pLSTM: parallelizable Linear Source Transition Mark networks