Rose Yu

Associate Professor@University of California, San Diego·美国·OpenReview

研究方向

deep learning · sequence modeling · spatiotemporal reasoning · time series analysis · physics-guided learning · dynamical systems · tensor methods · optimization

Rose Yu

Zephyrus: An Agentic Framework for Weather Science

Hilbert: Recursively Building Formal Proofs with Informal Reasoning

Finding Symmetry in Neural Network Parameter Spaces

Functional-level Uncertainty Quantification for Calibrated Fine-tuning on LLMs

Emergence of Hierarchical Emotion Organization in Large Language Models

SimulRAG: Simulator-based RAG for Grounding LLMs in Long-form Scientific QA

Steering LLMs' Reasoning With Activation State Machines

CAED-Agent: an Agentic Framework to Automate Simulation-Based Experimental Design

Discovering Symbolic Differential Equations with Symmetry Invariants

CaTS-Bench: Can Language Models Describe Numeric Time Series?

MOLLEO+: Towards Optimized Use of LLMs for Drug Discovery

Data-Free Transformer Quantization Using Parameter-Space Symmetry

Elucidated Rolling Diffusion Models for Probabilistic Forecasting of Complex Dynamics

VICON: Vision In-Context Operator Networks for Multi-Physics Fluid Dynamics

ClimaQA: An Automated Evaluation Framework for Climate Question Answering Models

Conformal Prediction for Time-series Forecasting with Change Points

Discovering Symbolic Differential Equations with Symmetry Invariants

AtlasD: Automatic Local Symmetry Discovery

Understanding Mode Connectivity via Parameter Space Symmetry

Adapting While Learning: Grounding LLMs for Scientific Problems with Tool Usage Adaptation

Functional-level Uncertainty Quantification for Calibrated Fine-tuning on LLMs

Understanding Mode Connectivity via Parameter Space Symmetry

Discovering Latent Causal Graphs from Spatiotemporal Data

MF-LAL: Drug Compound Generation Using Multi-Fidelity Latent Space Active Learning

Can LLMs Understand Time Series Anomalies?

MF-LAL: Drug Compound Generation Using Multi-Fidelity Latent Space Active Learning

ATLAS: Automatic Local Symmetry Discovery

Emergence of Hierarchical Emotion Representations in Large Language Models

Diff-BBO: Diffusion-Based Inverse Modeling for Black-Box Optimization

Discovering Latent Structural Causal Models from Spatio-Temporal Data

Finding Symmetry in Neural Network Parameter Spaces