Findings show that compression can alter the scores behind unchanged answers, but do not establish a reliable benefit from adjusting precision for each question, and whether choosing different groups for each question offers benefits beyond shuffled controls is tested.
Sourajit Saha, Shubhashis Roy Dipta, Shaswati Saha et al.· 1 citation
The system is a single 2B vision-language model that answers multiple-choice questions about ten-minute egocentric videos in one greedy forward pass, and reaches 89% of the accuracy of the large agentic pipeline using 1.1% of its parameters.
An automated pipeline is proposed that derives an actionable representation of a cyberattack from heterogeneous CTI sources and produces an enriched Attack Graph that captures a coarse, tactic-aligned progression of the attack and annotates each step with explicit pre-conditions and post-conditions, and an enriched des...
Nicola Deidda, L. Regano, Alessandro Sanna et al.· 0 citations
PrivEscalate is presented, a large-scale benchmark for Linux privilege escalation, comprising 531 Dockerized scenarios spanning 14 sub-categories and PrivEscalate, a domain-specialized wrapper that augments a generic ReAct agent with deterministic enumeration, category matching, and step planning that improves over pri...
Yi-Xuan Liu, Zi-Long Zhen, Yin Wu et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
A controlled cross-paradigm benchmark is presented to establish a substantial performance advantage for domain-specific fine-tuning over the evaluated zero-shot approaches and establish a controlled cross-paradigm benchmark for comparing detection paradigms for underground personnel perception.
Unknown authors· Italian National Conference...· 0 citations
Larger, methodologically rigorous trials using standardized light parameters, standardized outcome measures, and direct circadian assessments are needed to clarify the clinical effects of BLT and identify optimal treatment protocols.
Xiao-Lan Tang, Qiu-Ping Gu, Yang Zhan et al.· Frontiers in Neurology· 0 citations
Federal Reserve press conferences convey policy path information and uncertainty beyond formal decisions. This study tests whether transcript-derived risk language predicts the magnitude of financial market responses after policy surprises and event characteristics enter the model. The dataset contains 93 official pres...
Unknown authors· Journal of Risk and Financia...· 0 citations
A Neuro-Symbolic framework that closes this gap by tightly coupling a Vision-Language Model for automatic First-Order Logic rule induction with a Dynamic Logic Tensor Network for differentiable rule verification, in a closed iterative feedback loop is proposed.
Homayoun Afshari, Pietro Basci, A. Russo et al.· 0 citations
Testing the ability of common large language models to consider design principles to generate de novo proteins that bind metals and lipophilic small molecules without copying existing sequences highlights the utility of LLMs in making protein design more comprehensible and accessible to users without sophisticated desi...
Nam Hyeong Kim, A. K. Hatstat, Hyunil Jo et al.· bioRxiv· 1 citation
SpecGuard is introduced, an inference-time backdoor detector that repurposes speculative decoding at zero added model-computation cost and doubles as a free, always-on signal for detecting backdoored LLM behavior.
Wen Rui, Ahmed Salem, Andrew Paverd et al.· 0 citations
Generative AI and the practice of"vibe coding"are changing how archaeologists carry out computational research, but their effects on the discipline's range of methods is still understudied. In this paper, we evaluate whether large language models (LLMs) are narrowing the variety of methods archaeologists use. We first...
