Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2601. 14300v4 Announce Type: replace Abstract: Hard-label black-box attacks, relying solely on top-1 predictions, represent one of the most challenging yet practically threat models.
arXiv:2605. 29975v2 Announce Type: replace Abstract: We present a fully convolutional denoising autoencoder (FC-DAE) tailored for two-dimensional representations of dynamic correlations that is applicable to many experimental techniques.
arXiv:2602. 07339v2 Announce Type: replace Abstract: Diffusion-based trajectory planners can model multi-modal driving behavior, but their iterative denoising process introduces a latency bottleneck for real-time closed-loop deployment.
arXiv:2607. 28669v1 Announce Type: new Abstract: We present LARA (Lightweight Additive Residual Adaptation), a method for efficient adaptation that operates in the residual stream of a frozen model rather than in its weights.
arXiv:2607. 29078v1 Announce Type: new Abstract: On-policy distillation (OPD) trains student models on their own rollouts to reduce exposure bias.
arXiv:2607. 28862v1 Announce Type: cross Abstract: The rapid development of Large Language Models (LLMs) has led to significant advances across a wide range of language tasks, while simultaneously raising growing concerns about unauthorized data exploitation and privacy leakage.
arXiv:2607. 28881v1 Announce Type: new Abstract: As more responsibility is placed upon AI systems, it becomes increasingly important to guarantee that these systems are aligned with humanity.
arXiv:2501. 04426v2 Announce Type: replace-cross Abstract: Offline diversity maximization under imitation constraints can transform demonstration data into a set of distinct behavioral policies, improving robustness to distribution shift without additional environment interaction.
arXiv:2607. 28801v1 Announce Type: cross Abstract: Benchmark datasets are central to evaluating Large Language Models (LLMs), yet they are typically conceived as monolithic tasks, obscuring substantial variation in the demands of individual samples.
arXiv:2607. 28759v1 Announce Type: cross Abstract: In X-ray CT, metallic objects cause beam hardening, photon starvation, and scattering, leading to projection inconsistency, streaks, dark bands, and structural distortions that compromise clinical diagnosis and quantitative analysis.
arXiv:2607. 28672v1 Announce Type: cross Abstract: When a neural network predicts a physical system accurately, has it learned the governing law as formal, structured knowledge, and if so, does the network's internal computation actually use that representation throughout the law's domain of validity?
arXiv:2607. 28681v1 Announce Type: cross Abstract: Functional magnetic resonance imaging (fMRI) is a widely used technique for studying the brain.
arXiv:2607. 28916v1 Announce Type: cross Abstract: Multistep credit assignment is critical for sample-efficient reinforcement learning, yet managing off-policy bias in Q-learning remains a fundamental challenge.
arXiv:2410. 06665v4 Announce Type: replace-cross Abstract: This paper explores the characterization of equivariant linear layers for representations of permutations and related groups.
arXiv:2607. 27690v2 Announce Type: replace-cross Abstract: We introduce LabEvolver, a training-free framework that equips safe and grounded wet-lab agents with episodic memory from execution experience.
arXiv:2607. 29093v1 Announce Type: cross Abstract: Metasignal is an open-source Python package for signal detection theory (SDT) and metacognitive measurement.
arXiv:2607. 00064v2 Announce Type: replace Abstract: As technology advances, various algorithms have been proposed for air traffic management, yet their operational adoption in tactical control remains limited.
arXiv:2607. 28641v1 Announce Type: cross Abstract: We introduce the \textit{Agentic Formalism Trap} and the Evaluative Dissonance Index ($D_E$), quantifying how LLM-as-a-Judge systems conflate structural proceduralism with semantic truth under adversarial load.
arXiv:2607. 29657v1 Announce Type: new Abstract: Fault detection and diagnosis (FDD) technology is essential for improving HVAC system reliability, energy efficiency, and maintenance effectiveness.
arXiv:2607. 29254v1 Announce Type: new Abstract: AI agents extend large language models (LLMs) with external tools, enabling them to perform complex tasks and translate model outputs into consequential real-world actions.