Researchers at the University of Nebraska–Lincoln CPN Lab introduce Sensor Slicing, or SL,…
DNeo targets speculative-diffusion decoding by redesigning how a small parallel drafter co…
An arXiv preprint introduces self-rewriting: an already trained 27B model uses its own wei…
The study models an expert human researcher as a proxy saboteur and asks auditors to deter…
This study audits SAR vehicle recognition on MSTAR and ATRNet-STAR and finds that near-99%…
The paper stress-tests whether a model can deliberately make its chain of thought difficul…
The paper separates three claims often conflated in confidence-based LLM-agent systems: di…
This arXiv preprint defines sycophancy as inappropriate agreement: a model confirms a user…
Limite has released Limite 1B - Violetto, a one-billion-parameter model designed as a low-…
MInfoVisQA introduces a parallel question-answering benchmark for information-rich visual …
Sleep2Word frames EEG-informed sleep analysis without EEG hardware as a cross-modal discre…