From the 1 of 7 linked papers with an AI index.
7 papers
RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories
Roy Rinberg, Usha Bhalla, Igor Shilov +2
The paper presents RippleBench, a benchmark that automatically creates multiple‑choice questions about semantically related concepts using a Wikipedia‑based retrieval system, to me…
Haiku to Opus in Just 10 bits: LLMs Unlock Large Compression Gains
Roy Rinberg, Annabelle Michael Carrell, Simon Henniger +2
We study the compression of LLM-generated text across lossless and lossy regimes, characterizing a compression-compute frontier where more compression is possible at the cost of mo…
Beyond Laplace and Gaussian: Exploring the Generalized Gaussian Mechanism for Private Machine Learning
Roy Rinberg, Ilia Shumailov, Vikrant Singhal +2
Differential privacy (DP) is obtained by randomizing a data analysis algorithm, which necessarily introduces a tradeoff between its utility and privacy. Many DP mechanisms are buil…
Verifying LLM Inference to Detect Model Weight Exfiltration
Roy Rinberg, Adam Karvonen, Alexander Hoover +2
As large AI models become increasingly valuable assets, the risk of model weight exfiltration from inference servers grows accordingly. An attacker controlling an inference server…
Easy Data Unlearning Bench
Roy Rinberg, Pol Puigdemont, Martin Pawelczyk +1
Evaluating machine unlearning methods remains technically challenging, with recent benchmarks requiring complex setups and significant engineering overhead. We introduce a unified…
GenAI for Systems: Recurring Challenges and Design Principles from Software to Silicon
Arya Tschand, Chenyu Wang, Zishen Wan +21
Generative AI is reshaping how computing systems are designed, optimized, and built, yet research remains fragmented across software, architecture, and chip design communities. Thi…