🏢 University of Illinois at Urbana-Champaign

R-NeuralUCB: A robust neural contextual bandit algorithm uses a context-aware gradient descent training to defend against adversarial reward corruptions, achieving better performance with theoretical …

Persistent Test-Time Adaptation (PeTTA) prevents AI model collapse in recurring scenarios by dynamically adjusting the adaptation strategy based on divergence from the initial model, ensuring long-ter…

KG-FIT boosts knowledge graph embedding by smartly integrating open-world knowledge from LLMs, achieving significant performance gains.

INSTRUCTG2I: a novel graph context-conditioned diffusion model, generates images from multimodal attributed graphs, addressing challenges in graph size, dependencies, and controllability.

DeepDRK, a novel deep learning approach, significantly improves feature selection by effectively balancing false discovery rate and power, surpassing existing methods, especially with limited data.

New framework reveals LLMs’ human-like decision-making tendencies but highlights significant variations and biases influenced by demographic factors, underscoring ethical deployment needs.

Cascade Speculative Drafting (CS Drafting) dramatically speeds up large language model inference by using a multi-stage drafting process, optimizing both time allocation and autoregressive generation.