Autonomous cyber operations increasingly depend on agents that can chain reconnaissance, exploitation, and analysis across many tools while maintaining state over long task horizons. Large Language Models (LLMs) are promising orchestrators for this workflow, but naive agents that pipe model output directly into a shell...
James Hugglestone, Samuel Jacob Chacko, Dawson Stoller et al.· 0 citations
Safety alignment does not fully prevent large language models (LLMs) from producing harmful content under adversarial attacks. We observe that existing attack methods typically move harmful embeddings toward regions of harmless embeddings. This motivates us to explore whether increasing the distance between harmful and...
This work proposes a specification-aware action distribution optimization framework that enforces a broad class of Signal Temporal Logic constraints during execution of a pretrained robotics foundation model without modifying its parameters.
Sadik Bera Yüksel, Derya Aksaray· arXiv.org· 0 citations
An open, reproducible biomedical knowledge graph ecosystem built on Samyama, a Rust-native graph database that describes a reproducible ETL and portable .sgsnap snapshot pattern where graphs load alone or compose into one store.
Machine-learned interatomic potentials (MLIPs) are deployed for high-throughput materials screening without formal reliability guarantees. We show that a single MLIP used as a stability filter misses 93% of density functional theory (DFT)-stable materials (recall 0.07) on a 25,000-material benchmark. Proof-Carrying Mat...
A capable surgical AI model should reason from visual evidence; yet, many existing surgical benchmarks can be partially solved without visual input, as models may exploit procedural priors or common anatomy-instrument interactions to infer answers from language alone. To address this, we introduce SUREON, a video quest...
Alejandra Perez, Anita Rau, Busisiwe Mlambo et al.· 0 citations
Video object insertion is fundamental to video editing, yet existing diffusion methods often produce visually plausible but physically inconsistent results. We present Place-it-R1, an end-to-end framework for physically plausible video object insertion driven by environment-aware MLLM reasoning. Rather than treating re...
Generalized additive models (GAMs) offer high interpretability through independent univariate feature effects but underfit when interactions are present in data. GA$^2$Ms add selected pairwise interactions which improves accuracy, but sacrifices interpretability. We propose Conditionally Additive Local Models (CALMs),...
Vasilis Gkolemis, Loukas Kavouras, Dimitrios Kyriakopoulos et al.· 0 citations
This paper introduces a novel recovery-based shielding framework that enables safe RL with a provable safety lower bound for unknown and non-linear continuous dynamical systems.
Alexander W. Goodall, Francesco Belardinelli· Adaptive Agents and Multi-Ag...· 2 citations
JudgeGPT and RogueGPT are presented, a dual-axis framework that decouples ''authenticity'' from ''attribution'' to investigate the mechanisms of human susceptibility and suggest that ''pre-bunking'' interventions should target cognitive source monitoring rather than demographic segmentation to ensure trustworthy inform...
Alexander Loth, Martin Kappes, Marc-Oliver Pahl· The Web Conference· 10 citations
TIRx is presented, an ML compiler for GPUs and AI accelerators that exposes these ingredients through explicit interfaces and introduces tile-primitive dispatch, which lowers high-level operations to efficient implementations according to scope, layout, and backend.
Bo-Han Hou, H. Jin, Guan-Jie Wang et al.· 6 citations· ⚡2
Understanding the structure of complex, nonstationary, high-dimensional time-evolving signals is a central challenge in scientific data analysis. In many domains, such as speech and biomedical signal processing, the ability to learn disentangled and interpretable representations is critical for uncovering latent genera...
Ioannis N. Ziogas, Aamna Al Shehhi, Ahsan H. Khandoker et al.· 0 citations
