Associate Professor, Nanjing University
3 papers at NeurIPS 2025
We propose a novel MOE-based architecture that combines the detector and the visual foundation model for cross-domain few-shot object detection.
We investigate last-iterate convergence of Regret Matching$^+$ variants in games satisfying the weak Minty variation inequality.
We present the first parameter-free last-iterate convergence of Counterfactual Regret Minimization algorithms.
