Yang Yu

20

Papers

68

Total Citations

Papers (20)

ACT: Empowering Decision Transformer with Dynamic Programming via Advantage Conditioning

Generalizable Task Representation Learning for Offline Meta-Reinforcement Learning with Data Limitations

Reward-Consistent Dynamics Models are Strongly Generalizable for Offline Reinforcement Learning

Efficient Multi-agent Offline Coordination via Diffusion-based Trajectory Stitching

VA-AR: Learning Velocity-Aware Action Representations with Mixture of Window Attention

Episodic Return Decomposition by Difference of Implicitly Assigned Sub-trajectory Reward

GRAIN: Multi-Granular and Implicit Information Aggregation Graph Neural Network for Heterophilous Graphs

LLM Data Selection and Utilization via Dynamic Bi-level Optimization

Causality Based Front-door Defense Against Backdoor Attack on Language Models

Debiased Offline Representation Learning for Fast Online Adaptation in Non-stationary Dynamics

Deep Demonstration Tracing: Learning Generalizable Imitator Policy for Runtime Imitation from a Single Demonstration

MedUnifier: Unifying Vision-and-Language Pre-training on Medical Data with Vision Generation Task using Discrete Visual Representations

Policy-conditioned Environment Models are More Generalizable

GuideNER: Annotation Guidelines Are Better than Examples for In-Context Named Entity Recognition

Unmixing Before Fusion: A Generalized Paradigm for Multi-Source-based Hyperspectral Image Synthesis

Learning to Reuse Policies in State Evolvable Environments

Limited Preference Aided Imitation Learning from Imperfect Demonstrations

Offline Transition Modeling via Contrastive Energy Learning

ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models

Energy-Guided Diffusion Sampling for Offline-to-Online Reinforcement Learning