PPL
Jun Wang
Papers (6)
GS-FUSE: Granger-Supervised Gated Fusion and Multi-Granularity Alignment for Event-Driven Financial ForecastingTIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert OffloadSkills on the Fly: Test-Time Adaptive Skill Synthesis for LLM AgentsPosition: Agentic AI System Is a Foreseeable Pathway to AGILithoBench: Benchmarking Large Multimodal Models for Remote-Sensing Lithology InterpretationCASCADE: Case-Based Continual Adaptation for Large Language Models During Deployment