Kaiyi Ji

Minimax Optimal Adversarial Reinforcement Learning

LDC-MTL: Balancing Multi-Task Learning through Scalable Loss Discrepancy Control

ReciNet: Reciprocal Space-Aware Long-Range Modeling for Crystalline Property Prediction

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs

Distributionally Robust Bayesian Optimization: From Single to Multiple Objectives

GRID: Scalable Task-Agnostic Prompt-Based Continual Learning for Language Models

Tuning-Free Bilevel Optimization: New Algorithms and Convergence Analysis

MGDA Converges under Generalized Smoothness, Provably

Why Fine-Tuning Struggles with Forgetting in Machine Unlearning? Theoretical Insights and a Remedial Approach

Finite-Time Analysis for Conflict-Avoidant Multi-Task Reinforcement Learning

Enhancing Diffusion Posterior Sampling for Inverse Problems by Integrating Crafted Measurements