Kai Yang

9

Papers

4

Total Citations

Papers (9)

From Sequence to Structure: Uncovering Substructure Reasoning in Transformers

NeurIPS 2025arXiv

Contextures: Representations from Contexts

Novelty-Guided Data Reuse for Efficient and Diversified Multi-Agent Reinforcement Learning

Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model

GPU-Accelerated Parallel Bilevel Optimization for Roubst 6G ISAC

Two Stones Hit One Bird: Bilevel Positional Encoding for Better Length Extrapolation

Triadic-OCD: Asynchronous Online Change Detection with Provable Robustness, Optimality, and Convergence

Exploration and Anti-Exploration with Distributional Random Network Distillation

Do Efficient Transformers Really Save Computation?