VR-FraudNet, a five-stage framework combining a time-conditioned spectral graph encoder, LightGBM triage and threshold routing, a schema-constrained rationale language model, a fixed deterministic verifier, and an isotonic probability mixer with split-conformal calibration, does not establish universal adversarial safe...
Md Sultanul Arefin Sourav, Evha Rozario, Md Ashiqul Islam et al.· Discover Artificial Intellig...· 0 citations
A controlled counterfactual audit of 80 recent English-language arXiv manuscripts shows that metadata perturbations can displace manuscripts and alter top-K shortlist membership, identifying a concrete reliability risk for LLM-assisted scientific evaluation pipelines.
Marco Rospocher· Discover Artificial Intellig...· 0 citations
The results show that harness-managed control flow can substantially improve the effectiveness of the smallest models and suggest that small models can be useful for repository repair when responsibilities are divided across explicit stages that can be independently assigned to the component best suited to each.
Francesco Dente, Dario Satriani, Donatello Santoro et al.· Proceedings of the 1st Inter...· 0 citations
Deploying Large Language Models (LLMs) on memory-constrained edge servers to serve requests from mobile devices is challenging due to their substantial resource demands. The Key-Value (KV) cache and Feed-Forward Network (FFN) parameters consume the majority of available memory. However, existing methods typically rely...
Zhong-Xiang Wei, Yi-Peng Zhou, Jin Zhao et al.· IEEE Transactions on Mobile...· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
OrthoPurify is proposed, a more efficient method to purify backdoored model weights via one-step orthogonal projection, which reduces the attack success rate to near zero while preserving the original performance across diverse benchmarks, without retraining the backdoored model or introducing inference-time overhead.
Bo Yang, Hao-Chen Zhou, Zhi-Fang Zhang et al.· 0 citations
This work constructs a signal by force-decoding a fixed set of candidate answers and develops a framework that manipulates the image and question text separately, making the boundary searchable for any behaviour formulated as a choice between candidate answers.
R. Kaiser· Proceedings of the 41st IEEE...· 0 citations
Abstract interpretation provides a generic framework to design static analysis, and has been widely applied in analysis of real-world programs. The scalability and precision of these analyses depend largely on the chosen abstract domain. The template polyhedra domain is well-known for offering a compelling trade-off be...
Ren-Jie Huang, Li-Qian Chen, Hong-Fei Fu et al.· Proceedings of the 41st IEEE...· 0 citations
Linking people's appearance and actions to character identities is essential for understanding video narratives. We present a framework for identity-aware video captioning and person-centric question answering that combines automatic character identification, explicit spatial grounding, and task-specific adaptation. St...
A. F. Razzouki, Killian Steunou, Khalil Guetari et al.· 0 citations
COBOL remains one of the most widely deployed programming languages in mission-critical business systems, yet the pool of developers who can maintain it is shrinking. Automated translation to modern languages like Java is an increasingly attractive modernisation strategy, but systematic evaluation of available approach...
Joanna Abraham, Justyna Petke· Proceedings of the 2nd Inter...· 0 citations
Current frontier LLMs leverage vast training datasets with knowledge about a broad range of programming languages and frameworks, and can often solve tasks with minimal prompting. However, there are scenarios where remote LLMs are unsuitable, due to cost, privacy, security, or intellectual property concerns, and local...
Antonio García-Domínguez, Ionut Predoaia, T. Vu et al.· Proceedings of the 1st Inter...· 0 citations
Determining whether a test execution should pass or fail remains a core obstacle to end-to-end test automation. Recent work has focused mainly on generating assertions from source context, leav- ing open how much pass/fail signal can be recovered directly from runtime behavior, especially under subject transfer. We pre...
Giuliano Ricardo Rasper, T. Mammadov, Marius Smytzek et al.· Proceedings of the 1st Inter...· 0 citations
This work contributes a phonetically- and gender-balanced two-tier Bangladeshi Bangla corpus balanced via a tiered Jensen-Shannon divergence objective over conjunct clusters (juktakkhor), together with three fine-tuning changes: a merge-consistent tokenizer extension, Bangla text normalization, and a prompt-masked dual...
Emtiaz Uddin Ahmed, Araf Mahmud, S. Hossain et al.· 0 citations
Assistant Professor Benjamin Lindquist studies how engineers deliberately injected randomness into early AI, giving rise to deep-learning models that sometimes hallucinate.
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
