arXiv Machine Learning
Jun 30
Connectivity Estimation using Stochastic Graph Heat Modelling
arXiv:2606. 29098v1 Announce Type: cross Abstract: A growing number of techniques leverage the spatial structures that underlie many real-world datasets.
AI safety and alignment
Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv AI
Jun 30
Learned Coordination Conventions in Cooperative MARL: Measuring the Translation Gap Between Theory-Informed Roles and Learned Routing
arXiv:2606. 29541v1 Announce Type: new Abstract: Role-semantic assignments provide priors over how heterogeneous agents may coordinate, but cooperative MARL systems instead settle on conventions through decentralized, non-stationary learning, with no guarantee that the resulting structure matches those priors.
arXiv AI
Jun 30
Faults in Our Formal Benchmarking: Dataset Defects and Evaluation Failures in Lean Theorem Proving
arXiv:2606. 29493v1 Announce Type: new Abstract: Benchmarks for LLM-assisted theorem proving in Lean are often treated as intrinsically reliable because every solved instance comes with a machine-checked proof.
arXiv Machine Learning
Jun 30
Bridging the Gap Between Image Restoration and Navigational Safety in Hazy Conditions: A New Visibility Estimation Metric for Maritime Surveillance
arXiv:2606. 30049v1 Announce Type: cross Abstract: Visibility distance is critical to maritime navigational safety because it determines the effective observation range of shipborne and shore-based monitoring systems.
arXiv Machine Learning
Jun 30
FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks
arXiv:2606. 28962v1 Announce Type: cross Abstract: Model quantization is essential for the efficient deployment of Large Language Models (LLMs), but introduces a critical vulnerability: Quantization-Conditioned Backdoor (QCB) attacks.
arXiv Machine Learning
Jun 30
Federated Graph Learning for EV Charging Demand Forecasting with Personalization Against Cyberattacks
arXiv:2405. 00742v2 Announce Type: replace-cross Abstract: Mitigating cybersecurity risk in electric vehicle (EV) charging demand forecasting plays a crucial role in the safe operation of collective EV chargings, the stability of the power grid, and the cost-effective infrastructure expansion.
arXiv Machine Learning
Jun 30
The Forgetting-Retention Dilemma: Certified Unlearning Theory in Continual Learning
arXiv:2606. 29832v1 Announce Type: new Abstract: Machine unlearning aims to eliminate the influence of specific data from trained models to safeguard privacy.
arXiv AI
Jun 30
Deterministic Decisions for High-Stakes AI. A Zero-Egress Pipeline with the Deployability of RAG and the Accuracy of Machine Learning
arXiv:2606. 29280v1 Announce Type: cross Abstract: We identify intervention bias as a previously unquantified failure mode of zero-shot large-language-model (LLM) educational advisory agents: without task-specific training, they recommend action when a hindsight-optimal oracle policy mandates inaction.
arXiv AI
Jun 30
Whose Side Is Your Agent On? Multi-Party Principal Loyalty in LLM Agents
arXiv:2606. 30383v1 Announce Type: new Abstract: A rapidly growing class of LLM agents is multi-party: the agent acts for a principal (who briefs it, sends follow-ups, and receives results) while also conversing in a separate channel with a counterparty whose interests may diverge (negotiating with a vendor, screening inbound requests, or mediating between employees).
arXiv Machine Learning
Jun 30
Turn-Averaged SAEs for Feature Discovery and Long-Context Attribution
arXiv:2606. 28548v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have become a useful tool for extracting interpretable features in language models.
arXiv AI
Jun 30
BERTomelo: Your Portuguese Encoder Best Friend
arXiv:2606. 28999v1 Announce Type: cross Abstract: Encoders have become the state of the art for multiple NLP tasks, especially those requiring deep contextual understanding.
arXiv AI
Jun 30
Invariant Reasoning Directions in Latent Trajectories of Language Models
arXiv:2606. 29164v1 Announce Type: cross Abstract: Latent reasoning models perform multi-step inference directly in hidden-state space, yet the structure of these latent reasoning trajectories remains poorly understood.
arXiv AI
Jun 30
FADE: Mitigating Hallucinations by Reducing Language-Prior Dominance in Large Vision-Language Models
arXiv:2606. 29431v1 Announce Type: new Abstract: Despite the impressive capabilities of Large Vision-Language Models (LVLMs), they remain susceptible to hallucination, generating content inconsistent with the input image.
arXiv AI
Jun 30
Insidious by Design: Implications of Large Language Model algorithmic bias for the Global South
arXiv:2606. 28333v1 Announce Type: cross Abstract: \begin{quote} The biases in Large Language Models' (LLMs) outputs remain inadequately theorised, particularly from the perspective of the Global South.
arXiv AI
Jun 30
Agent Safety Is Action Alignment
arXiv:2606. 28739v1 Announce Type: new Abstract: Large language models increasingly act as agents: they call tools, move money, delete records, and send messages on a user's behalf.
arXiv AI
Jun 30
Categorizing Mathematical Concepts with LLM Voting Ensembles in Mathswitch
arXiv:2606. 28815v1 Announce Type: cross Abstract: Mathswitch is an open-source project that imports mathematical concept records from sources such as Wikidata, Wikipedia, MathWorld, Encyclopedia of Mathematics, nLab, ProofWiki, and Agda-Unimath, and links records that refer to the same concept.
arXiv AI
Jun 30
Evidence-Based Text-Conditioned 3D CT Synthesis for Ovarian Cancer
arXiv:2606. 28980v1 Announce Type: cross Abstract: Ovarian cancer is frequently diagnosed at an advanced stage, making preoperative contrast-enhanced computed tomography (CT) central to staging and surgical planning; yet the scarcity of annotated imaging data, compounded by privacy regulations, limits the development of generalizable computational models in this domain.
arXiv AI
Jun 30
HERO: Improving the Reliability and Sensitivity of Generative Model Evaluation Using Historical Data
arXiv:2606. 29784v1 Announce Type: cross Abstract: Reliable generative AI models critically rely on expert human annotations to evaluate output quality, yet these "gold" labels are expensive to collect and limited in quantity.
arXiv Machine Learning
Jun 30
HyperDFlash: Hyper-Connection-Aligned Block Speculative Decoding with Gated Residual Reduction
arXiv:2606. 26744v2 Announce Type: replace Abstract: We present HyperDFlash, a block-parallel speculative decoding framework tailored to DeepSeek-V4's Hyper-Connections (HC).
arXiv Machine Learning
Jun 30
From Failure Taxonomy to Intervention: A Diagnostic Methodology for Industry-Scale AVLM in Video and Live-Streaming Platform Moderation
arXiv:2606. 30059v1 Announce Type: new Abstract: Industry-scale video and live-streaming moderation imposes requirements that are difficult to satisfy with generic pretrained public models or external APIs, including adaptation to platform-specific data distributions, policy-specific objectives, and product-level safety constraints.