4 papers
Spike Hijacking in Late-Interaction Retrieval
Karthik Suresh, Tushar Vatsa, Tracy King +2
Late-interaction retrieval models rely on hard maximum similarity (MaxSim) to aggregate token-level similarities. Although effective, this winner-take-all pooling rule may structur…
CPT: Controllable and Editable Design Variations with Language Models
Karthik Suresh, Amine Ben Khalifa, Li Zhang +4
Designing visually diverse and high-quality designs remains a manual, time-consuming process, limiting scalability and personalization in creative workflows. We present a system fo…
Long-VMNet: Accelerating Long-Form Video Understanding via Fixed Memory
Saket Gurukar, Asim Kadav
Long-form video understanding is essential for various applications such as video retrieval, summarizing, and question answering. Yet, traditional approaches demand substantial com…
Automated Clinical Data Extraction with Knowledge Conditioned LLMs
Diya Li, Asim Kadav, Aijing Gao +2
The extraction of lung lesion information from clinical and medical imaging reports is crucial for research on and clinical care of lung-related diseases. Large language models (LL…