Yulia Tsvetkov

6 papers Department of Computer Science, University of Washington

• Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)
• Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)
• Escaping the SpuriVerse: Can Large Vision-Language Models Generalize Beyond Seen Spurious Correlations?
• Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems
• Precise Information Control in Long-Form Text Generation
• Sparta Alignment: Collectively Aligning Multiple Language Models through Combat