A PRM-free alignment pipeline combining genetic algorithm red teaming and multi-objective adversarial training is claimed to beat PRM-based methods at 61% lower cost, but the experiments are unverifiable.
Single-Source Shortest Paths with Negative Real Weights in $\tilde{O}(mn^{8/9})$ Time
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
This paper presents a randomized algorithm for the problem of single-source shortest paths on directed graphs with real (both positive and negative) edge weights. Given an input graph with $n$ vertices and $m$ edges, the algorithm completes in $\tilde{O}(mn^{8/9})$ time with high probability. For real-weighted graphs, this result constitutes the first asymptotic improvement over the classic $O(mn)$-time algorithm variously attributed to Shimbel, Bellman, Ford, and Moore.
fields
cs.CR 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training
A PRM-free alignment pipeline combining genetic algorithm red teaming and multi-objective adversarial training is claimed to beat PRM-based methods at 61% lower cost, but the experiments are unverifiable.