Flora D. Salim

Full Professor@University of New South Wales·澳大利亚·OpenReview

研究方向

spatio-temporal data · time-series · self-supervised learning · mobility modelling · transfer learning · unsupervised learning · computational social science

Flora D. Salim

DRIFT-Net: A Spectral-Coupled Neural Operator for PDEs Learning

Massive-STEPS: Massive Semantic Trajectories for Understanding POI Check-ins

HiT-JEPA: A Hierarchical Self-supervised Trajectory Embedding Framework for Similarity Computation

Generate the Forest before the Trees - A Hierarchical Diffusion model for Climate Downscaling

SOCIA: Joint Structure–Parameter Co-Optimization for Automated Simulator Construction

Hierarchical Sequence Iteration for Heterogeneous Question Answering

PACER: Physics Informed and Uncertainty Aware Climate Emulator

BLUE: Bi-layer Heterogeneous Graph Fusion Network for Avian Influenza Forecasting

EMAC+: Embodied Multimodal Agent for Collaborative Planning with VLM+LLM

Bisecle: Binding and Separation in Continual Learning for Video Language Understanding

Boosting Resilience of Large Language Models through Causality-Driven Robust Optimization

XXLTraffic: Expanding and Extremely Long Traffic forecasting beyond test adaptation

SensorLLM: Aligning Large Language Models with Motion Sensors for Human Activity Recognition

PAR-AdvGAN: Improving Adversarial Attack Capability with Progressive Auto-Regression AdvGAN

REVEAL-IT: REinforcement learning with Visibility of Evolving Agent poLicy for InTerpretability

Spectraformer: A Unified Random Feature Framework for Transformer

PACE: Physics Informed Uncertainty Aware Climate Emulator