Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2610.15351v1 Announce Type: cross Abstract: Amyotrophic lateral sclerosis (ALS) diagnosis remains challenging due to heterogeneous symptoms and reliance on clinical assessment, underscoring the...
arXiv:2610.19876v1 Announce Type: new Abstract: Continual learning aims to acquire new knowledge while retaining previously learned knowledge. However, updating shared parameters when learning new ta...
The paper presents a method for improving the robustness of deep reinforcement learning (DRL) policies used in planetary landing by employing adversarial reinforcement learning. A secondary agent generates physically constrained perturbations that challenge the landing controller, creating an asymmetric zero‑sum game. Training is conducted in three stages—baseline learning, stochastic robustness enhancement, and iterative adversarial optimization—showing that adversarial disturbances uncover vulnerabilities missed by conventional randomization and hint at better generalization to unseen perturbations.
arXiv:2506.19549v2 Announce Type: replace-cross Abstract: Identifying which tokens and activations truly influence model predictions is critical for both the efficiency and interpretability of large...
arXiv:2610.17665v2 Announce Type: new Abstract: Can vision-language models turn 2D observations into 3D understanding that supports precise action? This requires inferring object geometry, anticipati...
arXiv:2610.18095v1 Announce Type: new Abstract: AI companions provide users with emotional support and ongoing companionship, but their sustained relational interactions also introduce distinct safet...
arXiv:2610.14294v1 Announce Type: new Abstract: Conditional diffusion models can generate high-quality images that align closely with a given prompt. However, samples generated from different random...
arXiv:2610.14750v1 Announce Type: new Abstract: Credit assignment in modular financial reinforcement learning is difficult to evaluate because an attributed signal may improve a component loss withou...
arXiv:2610.14913v1 Announce Type: new Abstract: Reinforcement learning (RL) is essential for adaptive decision-making, e.g., robust Meta-RL and domain randomization (DR), and efficient post-training...
arXiv:2610.15231v1 Announce Type: new Abstract: Generative artificial intelligence (GenAI) models, particularly large language models (LLMs), are increasingly used in educational settings for tasks s...
arXiv:2610.15481v1 Announce Type: new Abstract: Independently authored skills can impose incompatible requirements, competing preferences, and redundant instructions when jointly loaded by an LLM age...
arXiv:2610.15449v2 Announce Type: new Abstract: Despite significant advances in language understanding, Large Language Models (LLMs) can still miss meaning hidden in plain sight, failing to identify...
arXiv:2610.15714v1 Announce Type: new Abstract: Healthcare agents must transform longitudinal clinical evidence into reliable actions through heterogeneous tools and stateful workflows, conditions un...
arXiv:2610.15948v1 Announce Type: new Abstract: Proactive Smart Assistants (PSAs) increasingly use general knowledge, learned patterns from group-level data, patterns from individual user's data, and...
arXiv:2610.16108v1 Announce Type: new Abstract: Maintaining up-to-date clinical practice guidelines (CPGs) is essential for evidence-based medicine, but rapid evidence growth and complex expert conse...
arXiv:2610.16927v1 Announce Type: new Abstract: Short-video search requires compact query rewriters that infer personalized intent from brief, ambiguous queries under strict latency constraints. The...
arXiv:2610.17158v1 Announce Type: new Abstract: When an LLM judge filters instruction-tuning data, its scoring format (binary verdict, 1--5 rating, 0--100 score, or comparison) is rarely justified or...
arXiv:2610.17610v2 Announce Type: new Abstract: Recently, the integration of generative priors has revolutionized Monocular Depth Estimation (MDE), achieving state-of-the-art (SOTA) performance with...
arXiv:2610.17757v1 Announce Type: new Abstract: Large language model agents can follow complex human instructions to solve real-world tasks. In practice, however, initial instructions are often incom...
arXiv:2610.18842v1 Announce Type: new Abstract: Robots are increasingly autonomous in task execution, yet their improvement remains largely human-driven. This study investigates Physical Recursive Se...