Yitao Liang

13

Papers

28

Total Citations

Papers (13)

Neural-Symbolic Recursive Machine for Systematic Generalization

ROCKET-1: Mastering Open-World Interaction with Visual-Temporal Context Prompting

Plug-and-Play Context Feature Reuse for Efficient Masked Generation

Tractable Transformers for Flexible Conditional Generation

Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction

Selecting Large Language Model to Fine-tune via Rectified Scaling Law

Open-World Skill Discovery from Unsegmented Demonstration Videos

ProAgent: Building Proactive Cooperative Agents with Large Language Models

Inference Aided Reinforcement Learning for Incentive Mechanism Design in Crowdsourcing

On Tractable Computation of Expected Predictions

Efficient Meta Reinforcement Learning for Preference-based Fast Adaptation

Describe, Explain, Plan and Select: Interactive Planning with LLMs Enables Open-World Multi-Task Agents

A Semantic Loss Function for Deep Learning with Symbolic Knowledge