arXiv AI
Jul 17
Pretraining Data Can Be Poisoned through Computational Propaganda
arXiv:2607. 15267v1 Announce Type: new Abstract: Poisoning pretraining data can introduce harmful behaviors to LMs that are difficult to detect and mitigate.
AI safety and alignment
Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv AI
Jul 17
SMC-ES: Automated synthesis of formally verified control policies
arXiv:2607. 15003v1 Announce Type: new Abstract: The deployment of autonomous cyber-physical systems in safety-critical environments requires closed-loop control strategies (i.
arXiv Machine Learning
Jul 17
Trajectory-Aware Flow Matching for Topology Optimisation
arXiv:2607. 14652v1 Announce Type: new Abstract: Topology optimisation (TO) often requires repeated finite element analysis and sensitivity-based material updates, which can be costly when multiple candidate designs are needed under varying physical and design conditions.
arXiv AI
Jul 17
Explainable Geospatial AI for Satellite Ground Station Siting Using LiDAR-Derived Terrain Intelligence
arXiv:2607. 14127v1 Announce Type: cross Abstract: Representative clutter height (RCH) is a key parameter in radio propagation and interference analysis because it captures the dominant height of local obstructions that drive terminal clutter loss.
arXiv Machine Learning
Jul 17
Decoding Market Emotion from Blockchain Activity: A Data-Driven Sentiment Classifier
arXiv:2607. 15258v1 Announce Type: new Abstract: The growing use of Bitcoin as a decentralized digital asset and investment tool has sparked strong interest in understanding its market behavior.
arXiv AI
Jul 17
The Misclassification of Autistic Writing as AI-Generated
arXiv:2607. 14729v1 Announce Type: cross Abstract: Recent findings suggest that detection models for artificial intelligence (AI) cannot accurately identify AI-generated text and may exhibit bias against certain minority groups.
arXiv AI
Jul 17
Energy-Efficient Federated Learning via Adaptive Encoder Freezing for MRI-to-CT Conversion: A Green AI-Guided Research
arXiv:2512. 03054v2 Announce Type: replace-cross Abstract: Federated Learning (FL) holds the potential to advance equality in health by enabling diverse institutions to collaboratively train deep learning (DL) models, even with limited data.
arXiv AI
Jul 17
CluCERT: Certifying LLM Robustness via Clustering-Guided Denoising Smoothing
arXiv:2512. 08967v2 Announce Type: replace-cross Abstract: Recent advancements in Large Language Models (LLMs) have led to their widespread adoption in daily applications.
arXiv AI
Jul 17
SceneBind: Binding What and Where Across Vision, Audio and Language
arXiv:2607. 15265v1 Announce Type: cross Abstract: We present SceneBind, an omni-modal representation of realistic scenes with joint semantic and 3D spatial understanding across vision, audio and language.
arXiv AI
Jul 17
Random Logit Scaling: Defending Deep Neural Networks Against Black-Box Score-Based Adversarial Example Attacks
arXiv:2607. 14921v1 Announce Type: cross Abstract: Machine learning models are increasingly adapted in various domains.
arXiv AI
Jul 17
Contextualized Evaluation of Vision Language Models through Dynamic, Multi-turn Interactions
arXiv:2607. 14499v1 Announce Type: new Abstract: Multi-modal Large Language Models (MLLMs) have made substantial advances on benchmarks, yet their real-world effectiveness remains uncertain.
arXiv AI
Jul 17
Breaking Refusal in the First Half: A Mechanistic Study of the Prefill Jailbreak
arXiv:2607. 14147v1 Announce Type: cross Abstract: Aligned language models refuse harmful requests, but a one-line prefill ("Sure, here is") strips the refusal.
arXiv AI
Jul 17
SmartRAG: Native Graph-Based RAG for Mobile Device
arXiv:2607. 14661v1 Announce Type: new Abstract: Deploying large language models (LLMs) as personal assistants on mobile devices demands privacy, low latency, and offline availability, yet the computational cost of giant models clashes with strict edge-hardware budgets.
arXiv AI
Jul 17
LBA: Textual Hard-Label Adversarial Attack under Low Query Budgets
arXiv:2607. 14101v1 Announce Type: cross Abstract: Generating high-quality adversarial texts with low query budgets remains a challenging problem in the hard-label scenario.
arXiv Machine Learning
Jul 17
Delocalization of bias in unadjusted Hamiltonian Monte Carlo and underdamped Langevin
arXiv:2607. 15208v1 Announce Type: cross Abstract: Unadjusted samplers such as unadjusted Hamiltonian Monte Carlo and underdamped Langevin are well-known to be biased.
arXiv AI
Jul 17
Towards Hierarchical Structure Understanding of Newspaper Images
arXiv:2607. 15082v1 Announce Type: cross Abstract: Understanding newspaper images remains a challenging task due to their complex, nested hierarchical structures and dense, heterogeneous layouts.
arXiv AI
Jul 17
Governing Artificial Intelligence: Public Preferences and Regulatory Options
arXiv:2607. 14585v1 Announce Type: cross Abstract: Artificial intelligence (AI) is rapidly transforming economies, societies, and polities, raising fundamental questions about how it should be regulated.
arXiv AI
Jul 17
Introspection Fine-Tuning (IFT): Training Small LLMs to Introspect
arXiv:2607. 14111v1 Announce Type: cross Abstract: Can small language models detect and report on perturbations their own internal activations?
arXiv AI
Jul 17
SafeRelBench: A Spatial-Relation-Aware Benchmark for Process-Level Safety in VLM-Driven Embodied Agents
arXiv:2607. 14543v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly used as the reasoning backbone of embodied agents, enabling robots to interpret visual scenes, follow language instructions, and plan multi-step actions.
arXiv AI
Jul 17
Steering Robustness into World Action Models via Mechanistic Interpretability and Optimal Control
arXiv:2607. 14943v1 Announce Type: cross Abstract: World Action Models (WAMs) enable semantically- and physically-informed control but are brittle under distribution shift.