17 papers
Output-Aware Rotation for INT2 KV-Cache Quantization
Vincent-Daniel Yun, Woosang Lim, Minsoo Cheong +4
The key-value (KV) cache has become a major memory and bandwidth bottleneck in long-context large language model inference, making ultra-low-bit quantization increasingly important…
Hair-Trigger Alignment: Black-Box Evaluation Cannot Guarantee Post-Update Alignment
Yavuz Bakman, Duygu Nur Yaldiz, Eleni Triantafillou +3
Large Language Models (LLMs) are rarely static and are frequently updated in practice. A growing body of alignment research has shown that models initially deemed ``aligned'' can e…
Rethinking Visual Privacy: A Compositional Privacy Risk Framework for Severity Assessment with VLMs
Efthymios Tsaprazlis, Tiantian Feng, Anil Ramakrishna +3
Existing visual privacy benchmarks largely treat privacy as a binary property, labeling images as private or non-private based on visible sensitive content. We argue that privacy i…
Robust Multi-Agent LLMs under Byzantine Faults
Haejoon Lee, Vincent-Daniel Yun, Dimitra Panagou +1
Large language model (LLM) agents increasingly collaborate over peer-to-peer networks to improve their reliability. However, these same interactions can also become a source of vul…
EPSVec: Efficient and Private Synthetic Data Generation via Dataset Vectors
Amin Banayeeanzade, Qingchuan Yang, Deqing Fu +6
High-quality data is essential for modern machine learning, yet many valuable corpora are sensitive and cannot be freely shared. Synthetic data offers a practical substitute for do…
Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs
Vincent-Daniel Yun, Junhyuk Jo, Sai Praneeth Karimireddy +1
Layer pruning removes entire Transformer decoder blocks from large language models, but introduces a mismatch between the hidden state received by the next surviving layer and the…