Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2606. 00105v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable progress on vision-language tasks, but they may also memorize and expose sensitive or restricted knowledge, raising concerns about privacy and broader safety risks.
arXiv:2606. 00106v1 Announce Type: cross Abstract: Brain-computer interfaces (BCIs) are limited by low signal-to-noise ratio in modalities such as electroencephalography, which requires multiple trials to reliably decode user intentions.
arXiv:2602. 02239v2 Announce Type: replace Abstract: Deep time series models continue to improve predictive performance, yet their deployment remains limited by their black-box nature.
arXiv:2606. 01279v1 Announce Type: new Abstract: AI agents are increasingly being tasked with automating AI research itself, particularly the critical post-training phase that transforms base LLMs into aligned assistants.
arXiv:2604. 10688v2 Announce Type: replace-cross Abstract: On-policy reinforcement learning has become the dominant paradigm for reasoning alignment in large language models, yet its sparse, outcome-level rewards make token-level credit assignment notoriously difficult.
arXiv:2606. 01895v1 Announce Type: cross Abstract: With the growing number of satellites in low Earth orbit (LEO) constellations, the near-Earth space environment has become increasingly congested, making space object detection (SOD) a pressing challenge for space safety and sustainability.
arXiv:2606. 01066v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) replaces human preference labels with executable reward functions such as math answer checkers, JSON tool-call validators, and code unit-test harnesses.
arXiv:2606. 01982v1 Announce Type: new Abstract: Schema-constrained information extraction from diverse educational and labor-market corpora remains an open challenge in natural language processing because existing pipelines rely primarily on lexical-surface methods that cannot recover implicit competencies, lack grounding in shared taxonomies, and provide no formal measures of extraction reliability or document-level completeness.
arXiv:2606. 01028v1 Announce Type: new Abstract: Medical treatment recommendation poses several challenges to reinforcement learning (RL): patient physiology evolves in continuous time, measurements and interventions are performed at irregular intervals, and treatment effects vary substantially across individuals.
arXiv:2606. 01952v1 Announce Type: new Abstract: As reinforcement learning (RL) increasingly applies to sensitive domains, such as health care and recommendation systems, privacy-preserving techniques have become essential to protect users' sensitive information.
arXiv:2602. 06547v3 Announce Type: replace-cross Abstract: LLM-based coding agents increasingly rely on third-party extensions called skills, which bundle natural language instructions and helper scripts that execute with full user privileges.
arXiv:2511. 16992v3 Announce Type: replace Abstract: Aligning Large Language Models (LLMs) with human values often involves balancing multiple, conflicting objectives such as helpfulness and harmlessness.
arXiv:2605. 20716v5 Announce Type: replace Abstract: Random forests construct each tree with a different, randomised representation of the feature space.
arXiv:2605. 21648v2 Announce Type: replace Abstract: We develop a mean-field theory of dropout as a perturbation of critical signal propagation at the edge of chaos, and show that it predicts a simple, no-cost change to standard practice: \emph{front-loaded} dropout schedules cut test loss by \(18\)--\(35\%\) over constant dropout in MLPs and Vision Transformers at fixed budget.
arXiv:2605. 12813v2 Announce Type: replace-cross Abstract: Large language models (LLMs) achieve strong performance across many tasks but remain vulnerable to hallucinations, making it important to systematically evaluate their reliability under realistic adversarial inputs.
arXiv:2606. 02177v1 Announce Type: new Abstract: Flow Matching typically relies on white noise sources, a choice often misaligned with the power spectra of natural data, which tend to decay with frequency.
arXiv:2606. 02530v1 Announce Type: new Abstract: Aligning Large Language Models (LLMs) with human values often degrades their general capabilities, termed the alignment tax.
arXiv:2605. 20301v2 Announce Type: replace-cross Abstract: In autonomous driving, 3D object detection is essential for accurate perception and reliable decision-making.
arXiv:2606. 02240v1 Announce Type: cross Abstract: Indirect prompt injection in tool-use agents is a concrete production threat: LLM agents read from integrations (third-party services such as Gmail, Salesforce, or Jira accessed through tool calls) whose response content the user neither writes nor controls.
arXiv:2605. 26310v2 Announce Type: replace Abstract: The detection of unmanned aerial vehicles (UAVs) is important for the protection of civilian and military infrastructure.