Search papers, labs, and topics across Lattice.
Affiliation:
8
51
8
38
This work studies adaptive routing of prompts to large language model experts to maximize response quality in an online setting with limited feedback and proposes algorithms that strategically select and observe rewards to minimize regret.
Forget reinforcement learning; this algorithm learns in real-time without any feedback at all.
Unlock face recognition with just one labeled example and a flood of unlabeled data, achieving state-of-the-art accuracy in a practical authentication scenario.
Learn user preferences across thousands of items from just tens of node evaluations by exploiting graph smoothness in a new spectral bandit framework.
LLMs are revolutionizing conversational AI research, and this survey offers a structured guide to navigating the rapidly evolving landscape of LLM-powered user simulation.
Forget direct prompt editing: this agentic planning framework, powered by offline RL and synthetic data, masters complex image styling by breaking it down into interpretable tool sequences.
Eye-tracking data can boost click prediction in carousel interfaces, but surprisingly, better click prediction doesn't always mean a better model of user behavior.
Spotting unusual labels in your data just got easier with a new method that avoids the pitfalls of flagging isolated or boundary cases as anomalies.
