2 citations · 2 across the 6 of their papers we have counts for
7 papers
Does Execution Require Target KV Fidelity? A Mixed-Fidelity KV Runtime for LLM Serving
Jiantong Jiang, Yue Yang, Peiyu Yang +1
Large language model (LLM) serving is increasingly constrained by the GPU memory consumed by key-value (KV) caches. Existing compression, eviction, and offloading techniques allevi…
Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization
Jiantong Jiang, Peiyu Yang, Rui Zhang +1
Despite the rapid advancements of large language models (LLMs), LLM serving systems remain memory-intensive and costly. The key-value (KV) cache, which stores KV tensors during aut…
MBD: A Model-Based Debiasing Framework Across User, Content, and Model Dimensions
Yuantong Li, Lei Yuan, Zhihao Zheng +27
Modern recommendation systems rank candidates by aggregating multiple behavioral signals through a value model. However, many commonly used signals are inherently affected by heter…
Attribution-Guided Model Rectification of Unreliable Neural Network Behaviors
Peiyu Yang, Naveed Akhtar, Jiantong Jiang +1
The performance of neural network models deteriorates due to their unreliable behavior on non-robust features of corrupted samples. Owing to their opaque nature, rectifying models…
Regulating Model Reliance on Non-Robust Features by Smoothing Input Marginal Density
Peiyu Yang, Naveed Akhtar, Mubarak Shah +1
Trustworthy machine learning necessitates meticulous regulation of model reliance on non-robust features. We propose a framework to delineate and regulate such features by attribut…
Fast-PGM: Fast Probabilistic Graphical Model Learning and Inference
Jiantong Jiang, Zeyi Wen, Peiyu Yang +2
Probabilistic graphical models (PGMs) serve as a powerful framework for modeling complex systems with uncertainty and extracting valuable insights from data. However, users face ch…
A Backdoor-based Explainable AI Benchmark for High Fidelity Evaluation of Attributions
Peiyu Yang, Naveed Akhtar, Jiantong Jiang +1
Attribution methods compute importance scores for input features to explain model predictions. However, assessing the faithfulness of these methods remains challenging due to the a…