SciAtlas is presented, a shared, machine-actionable cross-disciplinary scholarly knowledge infrastructure that integrates evidential, conceptual, disciplinary, expertise, and normative layers under a shared schema and achieves a unified neuro-symbolic retrieval mechanism that grounds heterogeneous research objects, propagates relevance across the scholarly topology, and projects the resulting relevance field into the context required by each scientific workflow.
Shuofei Qiao, Yun-Xiang Wei, Bu-Sheng Zhang et al.· 1 citation
Focusing on the autonomous driving safety-critical case of pedestrian detection in the dark, it is shown how synthetic low-light samples can be used to better characterize the performance of a state-of-the-art object detection model as a function of the scene illumination.
V. Pais, Malena Mendilaharzu, Daniele Faccio et al.· arXiv.org· 0 citations
Self-Anchored Consensus (SAC), a fully decentralized filter-and-refine protocol in which agents iteratively exchange responses, locally evaluate and filter unreliable messages, and refine their own outputs, is proposed.
Haejoon Lee, Vincent Yun, Hyeonho Oh et al.· arXiv.org· 3 citations
It is demonstrated that CoT encodes recoverable, token-level problem-solving information, offering new insight into how reasoning is represented and where it breaks down, suggesting complete reasoning chains are not always necessary.
Houman Mehrafarin, Amit Parekh, Ioannis Konstas· arXiv.org· 2 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work derives a closed-form expression for this adversarial perturbation, bypassing the iterative inner optimization of adversarial training entirely and enabling linear-time evaluation in the state dimension, and shows that this expression approximates the exact minimizer of the value function over the modeled uncertainty set with second-order accuracy.
Alex Zongo, Filippos Fotiadis, U. Topcu et al.· arXiv.org· 1 citation
PeopleSearchBench, an open-source benchmark comprising 119 multilingual queries across four scenarios: corporate recruiting, B2B sales prospecting, expert search, and influencer discovery, finds that multi-source search agents significantly outperform single-domain systems, particularly in influencer discovery where the performance gap is largest.
Tianyu Shi, Wei Wang, Zequn Xie et al.· 0 citations
This paper replicates and extends the system used in the AuTexTification shared task for authorship attribution of machine-generated texts, and tested newer multilingual language models and added 26 document-level stylometric features, using ablation, permutation importance, and SHAP analysis to assess feature influence.
Adam Skurla, D. Macko, Jakub Simko· arXiv.org· 0 citations
This work proposes a multi-stage alignment method that teaches models to recall and apply relevant business policies during chain-of-thought reasoning at inference time, without including the full business policy in-context.
Shubhashis Roy Dipta, Daniel Bis, Kun Zhou et al.· arXiv.org· 6 citations
This work proposes DesignAsCode, a novel framework that reimagines graphic design as a programmatic synthesis task using HTML/CSS, incorporating a Plan-Implement-Reflect pipeline, incorporating a Semantic Planner to construct dynamic, variable-depth element hierarchies and a Visual-Aware Reflection mechanism that optimizes the code to rectify rendering artifacts.
LSTR (Latent Sparse Transcoder Reasoning), a framework that turns sparse transcoders from post-hoc diagnostic tools into in-loop, intervenable transition components for latent reasoning, and suggests that sparse latent transitions can preserve the compression benefits of latent reasoning while making the resulting trajectories more inspectable and intervenable.
Yadong Wang, Hao-Dong Chen, Yu Tian et al.· 0 citations
SPADE (Soil moisture Pattern and Anomaly DEtection), which is the first LLM-based framework specifically developed for soil moisture time-series analysis, is proposed, which is the first LLM-based framework specifically developed for soil moisture time-series analysis.
Yeonju Lee, Rui-Qi Chen, Joseph Oboamah et al.· arXiv.org· 0 citations
Rank-One Safety Injection (ROSI), a white-box method that amplifies a model's safety alignment by permanently steering its activations toward the refusal-mediating subspace, is proposed, suggesting that targeted, interpretable weight steering is a cheap and potent mechanism to improve LLM safety, complementing more resource-intensive fine-tuning paradigms.
H. Shairah, Hasan Abed Al Kader Hammoud, G. Turkiyyah et al.· arXiv.org· 7 citations
