PPL
Yang Zhang
Papers (8)
When and How Human Curation Backfires: Preference Alignment under Multi-Model Self-Consuming LoopGS-FUSE: Granger-Supervised Gated Fusion and Multi-Granularity Alignment for Event-Driven Financial ForecastingLook on Demand: A Cognitive Scheduling Framework for Visual Evidence Acquisition in Multimodal ReasoningBeyond the Target: From Imitation to Collaboration in Speculative DecodingKnow You Before You Speak: User-State Modeling for LLM Personalization in Multi-Turn ConversationMultimodal Cultural Heritage Knowledge Graph Extension with Language and Vision ModelsFlowCompile: An Optimizing Compiler for Structured LLM WorkflowsLarge Language Models as Amortized Pareto-Front Generators for Constrained Bi-Objective Convex Optimization