Kai Yang

papers

707

total citations

papers (12)

A Unified Model for Multi-class Anomaly Detection

NEURIPS 2022arXiv

383

citations

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

CVPR 2024arXiv

209

citations

Exploration and Anti-Exploration with Distributional Random Network Distillation

ICML 2024arXiv

citations

Do Efficient Transformers Really Save Computation?

ICML 2024arXiv

citations

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

ICML 2024arXiv

citations

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

ICML 2024arXiv

citations

Contextures: Representations from Contexts

ICML 2025arXiv

citations

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

AAAI 2025arXiv

citations

GPU-Accelerated Parallel Bilevel Optimization for Roubst 6G ISAC

AAAI 2025

citations

Kai Yang

papers (12)

A Unified Model for Multi-class Anomaly Detection

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

Exploration and Anti-Exploration with Distributional Random Network Distillation

Do Efficient Transformers Really Save Computation?

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

Distributed Distributionally Robust Optimization with Non-Convex Objectives

ASM: Adaptive Skinning Model for High-Quality 3D Face Modeling

From Sequence to Structure: Uncovering Substructure Reasoning in Transformers

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

Contextures: Representations from Contexts

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

GPU-Accelerated Parallel Bilevel Optimization for Roubst 6G ISAC

papers (12)

A Unified Model for Multi-class Anomaly Detection

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

Exploration and Anti-Exploration with Distributional Random Network Distillation

Do Efficient Transformers Really Save Computation?

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

Distributed Distributionally Robust Optimization with Non-Convex Objectives

ASM: Adaptive Skinning Model for High-Quality 3D Face Modeling

From Sequence to Structure: Uncovering Substructure Reasoning in Transformers

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

Contextures: Representations from Contexts

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

GPU-Accelerated Parallel Bilevel Optimization for Roubst 6G ISAC