6 papers
Code-to-Harness: Distilling Black-Box Optimizers from Self-Play
Yi Wu, Zheng Ren, Zhiyu Hu +8
Can an agent learn a numerical search strategy through executable practice and then transfer that strategy as text? We study low-budget black-box optimization, where unaided langua…
ORBIT: Preserving Foundational Language Capabilities in GenRetrieval via Origin-Regulated Merging
Neha Verma, Nikhil Mehta, Shao-Chuan Wang +7
Despite the rapid advancements in large language model (LLM) development, fine-tuning them for specific tasks often results in the catastrophic forgetting of their general, languag…
Learning to Alleviate Familiarity Bias in Video Recommendation
Zheng Ren, Yi Wu, Jianan Lu +4
Modern video recommendation systems aim to optimize user engagement and platform objectives, yet often face structural exposure imbalances caused by behavioral biases. In this work…
Self-Evolving Recommendation System: End-To-End Autonomous Model Optimization With LLM Agents
Haochen Wang, Yi Wu, Daryl Chang +2
Optimizing large-scale machine learning systems, such as recommendation models for global video platforms, requires navigating a massive hyperparameter search space and, more criti…
Selecting User Histories to Generate LLM Users for Cold-Start Item Recommendation
Nachiket Subbaraman, Jaskinder Sarai, Aniruddh Nath +4
Large Language Models (LLMs) have demonstrated remarkable capabilities in reasoning, generalization, and simulating human-like behavior across a wide range of tasks. These strength…
ACT: Automated Constraint Targeting for Multi-Objective Recommender Systems
Daryl Chang, Yi Wu, Jennifer She +2
Recommender systems often must maximize a primary objective while ensuring secondary ones satisfy minimum thresholds, or "guardrails." This is critical for maintaining a consistent…