5 papers
RISR: Residual-Informed Scientific Equation Discovery with Large Language Models
Haobo Li, Wenshuo Zhang, Wenxiao Zhao +6
Symbolic regression combines structural search with numerical fitting, but aggregate fit scores do not describe how the remaining error varies across inputs. We introduce RISR, a r…
AutoSupervision: Closing the Feedback Loop in Scientific Workflows with Grounded Revision Verification
Haobo Li, Eunseo Jung, Wenxiao Zhao +8
Recent advances in large language models (LLMs) have enabled AI systems to assist scientific research and peer review. However, an essential capability for reliable AI-assisted sci…
Context-Driven Incremental Compression for Multi-Turn Dialogue Generation
Yeongseo Jung, Jaehyeok Kim, Eunseo Jung +5
Modern conversational agents condition on an ever-growing dialogue history at each turn, incurring redundant attention and encoding costs that grow with conversation length. Naive…
PIPE: Physics-Informed Position Encoding for Alignment of Satellite Images and Time Series
Haobo Li, Eunseo Jung, Zixin Chen +4
Multimodal time series forecasting is foundational in various fields, such as utilizing satellite imagery and numerical data for predicting typhoons in climate science. However, ex…
Towards a Unified Conversational Recommendation System: Multi-task Learning via Contextualized Knowledge Distillation
Yeongseo Jung, Eunseo Jung, Lei Chen
In Conversational Recommendation System (CRS), an agent is asked to recommend a set of items to users within natural language conversations. To address the need for both conversati…