Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 15740v1 Announce Type: cross Abstract: As Text-to-Image (T2I) systems rapidly advance, evaluating the cultural authenticity of synthesized content has become increasingly important for fair and trustworthy generative AI.
arXiv:2604. 10024v2 Announce Type: replace-cross Abstract: Long video summarization presents significant challenges for multimodal large language models (MLLMs), particularly in maintaining temporal fidelity over extended durations and producing summaries that are both semantically and temporally grounded.
arXiv:2607. 15440v1 Announce Type: new Abstract: We introduce Stochastic Reset Pathfinding (SRP), an episodic learning problem on a known directed graph with unknown stationary edge success probabilities.
arXiv:2607. 15606v1 Announce Type: new Abstract: Synthetic sequential tabular data are increasingly used for privacy-preserving data sharing, yet a generator can reproduce every marginal and every foreign-key relationship while emitting timestamps that run backwards or repeat, and while sending entities along paths that no real entity followed.
arXiv:2602. 24009v4 Announce Type: replace-cross Abstract: Jailbreak techniques for large language models (LLMs) evolve faster than benchmarks, making robustness estimates stale and difficult to compare across papers due to drift in datasets, harnesses, and judging protocols.
arXiv:2601. 22818v2 Announce Type: replace-cross Abstract: Fine-tuned LLMs can covertly encode prompt secrets into outputs via steganographic channels.
arXiv:2502. 11068v3 Announce Type: replace-cross Abstract: Anchors is a popular local model-agnostic explanation technique whose applicability is limited by its computational inefficiency.
arXiv:2607. 15433v1 Announce Type: new Abstract: We characterize and compare the inherent interpretability offerings of a standard linear model with a single qubit mixed state model for the task of supervised binary classification.
arXiv:2607. 15774v1 Announce Type: cross Abstract: Explainable AI (XAI) for time series has seen significant algorithmic growth, but its utility in providing measurable performance gains for downstream tasks remains under-explored.
arXiv:2412. 10665v3 Announce Type: replace-cross Abstract: We introduce a foundation model for event classification in high-energy physics, built on a Graph Neural Network architecture and trained on 120 million simulated proton-proton collision events spanning 12 distinct physics processes.
arXiv:2607. 15293v1 Announce Type: cross Abstract: Dyadic and circular convolution can both be computed in $O(N\log N)$ time using the Hadamard transform and the FFT-computed discrete Fourier transform (DFT), respectively.
arXiv:2607. 16178v1 Announce Type: cross Abstract: In many applications of matching, the point clouds to be matched are not merely unstructured sets of points but rather samples from distributions with an intrinsic cluster structure.
arXiv:2607. 15457v1 Announce Type: new Abstract: We study robust peak-cost constrained reinforcement learning (RP-CRL), where the objective is to maximize expected reward while controlling the maximum cost encountered along a trajectory.
arXiv:2607. 15861v1 Announce Type: cross Abstract: Moderation systems increasingly rely on external toxicity tools, but those tools are unreliable under code-mixing, transliteration, slang, and language mismatch.
arXiv:2607. 15286v1 Announce Type: cross Abstract: We investigate whether harmful chain-of-thought (CoT) traces from compromised language models can transfer unsafe behaviour and be distilled into reusable jailbreak attacks.
arXiv:2602. 17229v2 Announce Type: replace Abstract: The black-box nature of Large Language Models necessitates novel evaluation frameworks that transcend surface-level performance metrics.
arXiv:2605. 31259v2 Announce Type: replace Abstract: Unscheduled trips of high-power pulsed converters are a leading source of downtime at large accelerator facilities.
arXiv:2205. 04599v2 Announce Type: replace-cross Abstract: Explainable Artificial Intelligence (XAI) is essential for trustworthy AI in healthcare, yet many existing methods rely on technical explanations that are difficult for clinicians and patients to interpret.
arXiv:2607. 15589v1 Announce Type: cross Abstract: Communication-limited robots in mission-critical scenarios such as disaster inspection and search-and-rescue must make reliable onboard decisions without access to remote operators or high-capacity reasoning services.
arXiv:2511. 18468v2 Announce Type: replace Abstract: Continual Test-Time Adaptation (CTTA) is crucial for deploying models in real-world applications with unseen, evolving target domains.