LRMs
PulseAugur coverage of LRMs — every cluster mentioning LRMs across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New AdvSafe Framework Enhances LRM Safety Alignment
A new research paper introduces AdvSafe, a dual-adversarial framework designed to improve the safety alignment of Large Reasoning Models (LRMs). This method trains LRMs to understand and defend against harmful prompts b…
-
New research details complexity of entrywise power matrix factorization
A new arXiv paper delves into the computational complexity of entrywise power matrix factorization (EPMF), a technique used in various applications including the modulus model and componentwise square factorization. The…
-
New QMFOL framework generates controllable logic reasoning benchmarks for LLMs
Researchers have introduced QMFOL, a novel framework designed to generate quantifiable and controllable monadic first-order logic reasoning tasks. This system addresses limitations in existing benchmarks by allowing pre…
-
ReSET method boosts NVFP4 reasoning accuracy and speed
Researchers have developed ReSET, a novel method to improve the accuracy and efficiency of large reasoning models (LRMs) when using NVFP4 low-precision inference. ReSET addresses quantization-induced accuracy degradatio…