PPL
Bo Li
Papers (8)
GUI Agents for Continual Game GenerationMix-MoE: Improving Multilingual Machine Translation of Large Language Models through Mixed MoEsVaaWIT: Visual-Aware Adaptation of Large Language Models for Multilingual Web Image TranslationDual-Dimensional Consistency: Balancing Budget and Quality in Adaptive Inference-Time ScalingRewardHarness: Self-Evolving Agentic Post-TrainingCellScientist: Dual-Space Hierarchical Orchestration for Closed-Loop Refinement of Virtual Cell ModelsVisual Text Compression as Measure TransportEvolving Idea Graphs with Learnable Edits-and-Commits for Multi-Agent Scientific Ideation