Carl Yang

Assistant Professor@Emory University·美国·OpenReview

研究方向

Large language models · Multimodality foundation models · Knowledge graphs · Health informatics · Federated learning · Neuroscience · Data mining · Machine learning

Carl Yang

MedAgentGym: A Scalable Agentic Training Environment for Code-Centric Reasoning in Biomedical Data Science

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

Incentivizing Agentic Reasoning in LLM Judges via Tool-Integrated Reinforcement Learning

Beyond Chunks and Graphs: Retrieval-Augmented Generation through Triplet-Driven Thinking

SE-Diff: Simulator and Experience Enhanced Diffusion Model for Comprehensive ECG Generation

Bootstrapped Exploration with Causal Reasoning: A Training Paradigm for Adaptive Forecasting Agent

LUSB: Formalizing and Benchmarking Unlearning Attacks and Defenses against Large Language Models

MANI-Pure: Magnitude-Adaptive Noise Injection for Adversarial Purification

Peeling Context from Cause for Multimodal Molecular Property Prediction

PanaCea: Clinical Hypergraph Framework for Health-Aware Personalized Diet Recommendation

AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play

Subgraph Federated Learning for Local Generalization

Don’t Forget the Enjoin: FocalLoRA for Instruction Hierarchical Alignment in Large Language Models

EAGLES: Towards Effective, Efficient, and Economical Federated Graph Learning via Unified Sparsification

Collab-RAG: Boosting Retrieval-Augmented Generation for Complex Question Answering via White-Box and Black-Box LLM Collaboration

GuardAgent: Safeguard LLM Agents via Knowledge-Enabled Reasoning

GuardAgent: Safeguard LLM Agent by a Guard Agent via Knowledge-Enabled Reasoning

Attack as Defense: Run-time Backdoor Implantation for Image Content Protection

BoxLM: Unifying Structures and Semantics of Medical Concepts for Diagnosis Prediction in Healthcare

Contrastive Unlearning: A Contrastive Approach to Machine Unlearning

GC4NC: A Benchmark Framework for Graph Condensation on Node Classification with New Insights

Integrating Planning into Single-Turn Long-Form Text Generation

A Causal Theoretical Framework for Open Set Domain Adaptation

Are Synthetic Time-series Data Really not as Good as Real Data?