Bo Ji

GazeVLM: Gaze-Guided Vision-Language Models for Efficient and Robust Inference

SPLiT: Popularity-Bias-Aware Online Prompt Optimization for LLM-based Recommendation

HypRQ-VAE: Long-Tail-Aware Item Indexing for Generative Recommender Systems

Follow-the-Perturbed-Leader for Adversarial Bandits: Heavy Tails, Robustness, and Privacy

Taming Heavy-Tailed Losses in Adversarial Bandits and the Best-of-Both-Worlds Setting