Jianxi Gao

Intermediate Representations are Strong Training-Free AI-Generated Image Detectors

Optimality and NP-Hardness of Transformers in Learning Markovian Dynamical Functions

ADAPT: Adaptive Prompt Tuning for Pre-Trained Vision-Language Models

Language Models Are Good Tabular Learners

Global Optimality of In-context Markovian Dynamics Learning

Inferring from Logits: Exploring Best Practices for Decoding-Free Generative Candidate Selection