Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2604. 23099v2 Announce Type: replace-cross Abstract: Evaluating generative AI models is increasingly resource-intensive due to slow inference, expensive raters, and a rapidly growing landscape of models and benchmarks.
arXiv:2606. 02628v1 Announce Type: new Abstract: We investigate whether open-source LLMs encode a linearly separable truthfulness signal in their hidden states, and at which network depth this signal is strongest.
arXiv:2606. 02642v1 Announce Type: cross Abstract: Despite the success of audio-visual large-language models (LLMs), they can produce plausible but ungrounded outputs, termed hallucination.
arXiv:2506. 21129v2 Announce Type: replace-cross Abstract: Autonomous unmanned aerial vehicles (UAVs) increasingly rely on reinforcement learning (RL) for navigation.
arXiv:2606. 03936v1 Announce Type: new Abstract: Neural operator surrogates (NO) approximate PDE solutions orders of magnitude faster than numerical solvers, but suffer from spectral bias: high-frequency content is systematically attenuated, limiting reliability where fine-scale structure matters.
arXiv:2604. 18572v2 Announce Type: replace-cross Abstract: The Platonic Representation Hypothesis suggests that neural networks trained on different modalities (e.
arXiv:2606. 03569v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have demonstrated remarkable capabilities but suffer from significant computational overhead during inference.
arXiv:2606. 03094v1 Announce Type: new Abstract: Recent advances in language models have established reinforcement learning as the primary paradigm for eliciting self-correction and long-chain reasoning.
arXiv:2606. 03312v1 Announce Type: cross Abstract: While household robots are often evaluated based on task completion, everyday domestic environments involve value-conflicting situations in which robots are expected to choose actions that prioritize other values than task success, such as human autonomy, efficiency, or social appropriateness.
arXiv:2511. 13899v2 Announce Type: replace-cross Abstract: Low-rank recurrent neural networks (lrRNNs) are a class of models that uncover low-dimensional latent dynamics underlying neural population activity.
arXiv:2606. 02959v1 Announce Type: new Abstract: Published evaluations of prompt-injection and jailbreak detectors for Large Language Models often suffer from two systematic weaknesses: per-dataset threshold tuning and undisclosed operating points.
arXiv:2606. 02914v1 Announce Type: new Abstract: Background: Oral diseases affect nearly 3.
arXiv:2606. 03184v1 Announce Type: cross Abstract: Financial forecasting is difficult due to low signal-to-noise ratios, latent factors, heavy tails, regime shifts, and jumps.
arXiv:2605. 30155v3 Announce Type: replace-cross Abstract: The increasing integration of deep neural networks in critical systems has spawned a theoretical and practical interest in formally guaranteeing safety properties about their behavior.
arXiv:2606. 03199v1 Announce Type: new Abstract: Organic crystal structure prediction (CSP) is a requirement for computational modelling of organic solids, but traditionally costs several CPU-years per molecule.
arXiv:2606. 03808v1 Announce Type: cross Abstract: We propose PURGE, a machine unlearning algorithm built on a simple but an under-exploited observation: continual learning (CL) and machine unlearning (MU) which are fundamentally dual problems.
arXiv:2606. 03143v1 Announce Type: new Abstract: Modern LLM agents increasingly rely on skill libraries to handle complex tasks, making skill evolution a primary driver of self-improvement.
arXiv:2507. 19684v2 Announce Type: replace-cross Abstract: Socially interactive humanoid robots must engage with humans through their bodies, adapting in real time to a partner's movement, intent, and abilities.
arXiv:2606. 03131v1 Announce Type: new Abstract: Reward models are central to large language model (LLM) alignment, but they remain vulnerable to reward hacking.
arXiv:2604. 07366v2 Announce Type: replace Abstract: Partial differential equations (PDEs) govern nearly every physical process in science and engineering, but solving them at scale remains prohibitively expensive.