activity
20232026
most citedWhat Operations can be Performed Directly on Compressed Arrays, and with What Error?

5 citations · 6 across the 3 of their papers we have counts for

collaborators

5 papers

cs.CR2026

A Dark Forest First Attack Is Rational Only If the Attacker Accepts It as Its Last

Harvey Dam

The Dark Forest argument holds that a civilization that detects another should strike it at once, so detection, and any transmission that invites it, is danger. Existing models mak…

cs.CL20251 cited

Derailing Non-Answers via Logit Suppression at Output Subspace Boundaries in RLHF-Aligned Language Models

Harvey Dam, Jonas Knochelmann, Vinu Joseph +1

We introduce a method to reduce refusal rates of large language models (LLMs) on sensitive content without modifying model weights or prompts. Motivated by the observation that ref…

cs.LG2025

Local-Order Auxiliary Losses Can Improve Autoencoder Reconstruction

Harvey Dam, Martin Burtscher, Tripti Agarwal +1

Mean-squared error is the default objective for training autoencoders, yet compressed reconstructions often depend not only on pointwise accuracy but also on preserving local spati…

cs.DC20245 cited

What Operations can be Performed Directly on Compressed Arrays, and with What Error?

Tripti Agarwal, Harvey Dam, Dorra Ben Khalifa +3

In response to the rapidly escalating costs of computing with large matrices and tensors caused by data movement, several lossy compression methods have been developed to significa…

cs.DC2023

MPGemmFI: A Fault Injection Technique for Mixed Precision GEMM in ML Applications

Bo Fang, Xinyi Li, Harvey Dam +9

Emerging deep learning workloads urgently need fast general matrix multiplication (GEMM). To meet such demand, one of the critical features of machine-learning-specific accelerator…