Kun Kuang

Asynchronous Denoising Diffusion Models for Aligning Text-to-Image Generation

ExpertWeaver: Unlocking the Inherent MoE in Dense LLMs with GLU Activation Patterns

Efficient Ensemble Conditional Independence Test Framework for Causal Discovery

Can LLMs Reason Soundly in Law? Auditing Inference Patterns for Legal Judgment

FORGE: Forming Semantic Identifiers for Generative Retrieval in Industrial Datasets

Arrow: Accelerator for Time Series Causal Discovery with Time Weaving

Advancing Personalized Learning with Neural Collapse for Long-Tail Challenge

ERICT: Enhancing Robustness by Identifying Concept Tokens in Zero-Shot Vision Language Models

Generalizing Causal Effects from Randomized Controlled Trials to Target Populations across Diverse Environments

Latent Score-Based Reweighting for Robust Classification on Imbalanced Tabular Data

D-Fusion: Direct Preference Optimization for Aligning Diffusion Models with Visually Consistent Samples

Rethinking Causal Ranking: A Balanced Perspective on Uplift Model Evaluation