Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2608. 06834v1 Announce Type: new Abstract: Transformers provide a powerful architecture for global content-based matching, but reasoning problems may benefit from a stronger inductive bias toward iterative traversal of latent relations.
arXiv:2605. 18079v2 Announce Type: replace Abstract: Existing expressivity results for transformers typically rely on hardmax attention, high precision, and other architectural modifications that disconnect them from the models used in practice.
arXiv:2608. 06955v1 Announce Type: new Abstract: Large language models (LLMs) are trained on corpora that contain expressions of human judgment about films, books, music, and more.
arXiv:2608. 06394v1 Announce Type: new Abstract: Multi-label node classification is an important yet challenging task in graph learning, where nodes exhibit multiple semantics simultaneously.
arXiv:2608. 06776v1 Announce Type: new Abstract: A standard self-attention layer consists of two interacting circuits: the query-key circuit that governs attention allocation, and the output-value circuit that maps attended representations to predictions.
arXiv:2608. 07463v1 Announce Type: cross Abstract: Recent advances in video diffusion models (VDMs) have enabled high-fidelity video synthesis.
arXiv:2608. 06378v1 Announce Type: cross Abstract: Driver emotions can affect risk perception, decision-making, and vehicle control under complex road conditions.
arXiv:2608. 06908v1 Announce Type: cross Abstract: We propose Zero-phase Component Analysis (ZCA) whitening as a geometric pre-processing step for the Word Embedding Association Test (WEAT).
arXiv:2401. 07039v5 Announce Type: replace-cross Abstract: Mixed quantum states are the native description of many physically important quantum systems, making their generation a fundamental task in quantum information processing.
arXiv:2608. 06447v1 Announce Type: cross Abstract: In modern distributed network environments, particularly in Internet of Things infrastructures and 5G networks, stringent privacy preservation and scalability requirements have created significant challenges for intrusion detection systems.
arXiv:2608. 07228v1 Announce Type: new Abstract: When a reinforcement learning agent cannot observe the full state, we usually blame its policies: it cannot see enough to represent a good one.
arXiv:2608. 06477v1 Announce Type: cross Abstract: Computer-use agents (CUAs) face a growing threat from indirect prompt injection, where adversarial instructions are planted in the environment such as web pages.
arXiv:2608. 06823v1 Announce Type: cross Abstract: In this paper, we extend a weak adversary neural network pushforward method for solving time dependent Boltzmann equation and a weak formulation of the collision operator is proposed where an invertible neural pushforward mapping is used to generating samples given by the distribution governed by the Boltzmann equation.
arXiv:2608. 06948v1 Announce Type: new Abstract: AI models are becoming increasingly adept at understanding and processing spatial information, thereby facilitating agentic problem-solving in spatial tasks and workflows.
arXiv:2510. 09717v3 Announce Type: replace-cross Abstract: Identifying training data of large-scale models is critical for copyright litigation, privacy auditing, and ensuring fair evaluation.
arXiv:2608. 07302v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) often suffer from object hallucination, generating objects that are absent from the image.
arXiv:2608. 07151v1 Announce Type: cross Abstract: Reinforcement learning policies are difficult to inspect, but interpreting them is a prerequisite for trustworthiness.
arXiv:2608. 06638v1 Announce Type: cross Abstract: Mechanistic interpretability of music generation has concentrated on audio models, leaving symbolic models largely unexplored.
arXiv:2608. 07303v1 Announce Type: new Abstract: Comparisons between AutoML systems at short time budgets -- tens of seconds rather than hours -- are common in tool READMEs and workshop papers, and they are easy to get wrong.
arXiv:2603. 21607v2 Announce Type: replace Abstract: While retrieval-augmented generation (RAG) significantly improves the factual reliability of LLMs, it does not eliminate hallucinations, so robust uncertainty quantification (UQ) remains essential.