Rex Ying

Assistant Professor@Yale University·美国·OpenReview

研究方向

multimodal foundation model · time series · trustworthy deep learning · graph neural networks · AI for science · representation learning · geometric deep learning · recommender systems

Rex Ying

Seeing Through the Brain: New Insights from Decoding Visual Stimuli with fMRI

Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs

HEIST: A Graph Foundation Model for Spatial Transcriptomics and Proteomics Data

Platonic Transformers: A Solid Choice for Equivariance

TelecomTS: Observability Dataset for Multi-Modal Time-Series and Language Analysis

FlatLand: Personalized Graph Federated Learning via Tailored Lorentz Space

Parameter-Efficient Fine-Tuning of LLMs with Mixture of Space Experts

RepQA: Evaluating Readability of Large Language Models in Patient Education Question Answering

MTBench: A Multimodal Time Series Benchmark for Temporal Reasoning and Question Answering

Hyperbolic Fine-Tuning for Large Language Models

TRACE: Grounding Time Series in Context for Multimodal Embedding and Retrieval

HELM: Hyperbolic Large Language Models via Mixture-of-Curvature Experts

Scalable Generation of Spatial Transcriptomics from Histology Images via Whole-Slide Flow Matching

HiPoNet: A Multi-View Simplicial Complex Network for High Dimensional Point-Cloud and Single-Cell data

Non-Markovian Discrete Diffusion with Causal Language Models

Learning Along the Arrow of Time: Hyperbolic Geometry for Backward-Compatible Representation Learning

Hyperbolic Fine-tuning for Large Language Models

MindLLM: A Subject-Agnostic and Versatile Model for fMRI-to-text Decoding

Personalized Federated Learning via Tailored Lorentz Space

Predicting Spatial Transcriptomics from Histology Images via Biologically Informed Flow Matching

Retrieval-Augmented Language Model for Knowledge-aware Protein Encoding

GFSE: A Foundational Model For Graph Structural Encoding

Retrieval-Augmented Language Model for Knowledge-aware Protein Encoding

FIMP: Foundation Model-Informed Message Passing for Graph Neural Networks

DYSTIL: Dynamic Strategy Induction with Large Language Models for Reinforcement Learning