Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2604.26370v2 Announce Type: replace-cross Abstract: Vision-language models have shown strong performance, but they often generalize poorly to specialized domains. While semi-supervised vision-l...
arXiv:2610.19202v1 Announce Type: new Abstract: Rare but severe failures of large language models can become practically significant at deployment scale. Estimating their probabilities with direct Mo...
arXiv:2610.20221v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed across languages, yet their safety and reasoning capabilities remain predominantly evaluated in...
arXiv:2610.19063v1 Announce Type: new Abstract: As video models enable longer and more realistic interactive experiences, maintaining a world consistent with its history becomes essential. This requi...
arXiv:2610.20091v1 Announce Type: new Abstract: Video scene graph generation (VidSGG) aims to capture objects and their evolving relationships in videos. This requires accounting for both the persist...
arXiv:2603.12468v2 Announce Type: replace Abstract: Under strong cross-domain shifts, weakly supervised object localization (WSOL) models often lose their capacity to discriminate and develop a stron...
arXiv:2610.18573v1 Announce Type: cross Abstract: The stories told about artificial intelligence (AI) play a central role in shaping public understanding, policy debates, and expectations about techn...
arXiv:2610.18613v1 Announce Type: cross Abstract: Self-distillation is an emerging approach that trains a model to imitate its own predictions when conditioned on privileged information, such as corr...
arXiv:2608.24569v2 Announce Type: replace Abstract: Large language model (LLM) agents build on one another's work through summaries, plans, and other intermediate artifacts. These records let a downs...
arXiv:2610.11567v3 Announce Type: replace-cross Abstract: Battery state of health (SoH) forecasting is important for battery management, but remains challenging due to nonlinear degradation and heter...
arXiv:2610.16070v1 Announce Type: new Abstract: Frontier models are now trained for complex multi-agent tasks, from running a company to engaging in negotiations. These tasks necessitate training mod...
arXiv:2610.03998v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used as synthetic personas representing survey respondents. Their validity as substitutes for particu...
arXiv:2610.15994v1 Announce Type: new Abstract: Representing individual-level behavioral heterogeneity is challenging in epidemiological modeling, particularly when empirical behavioral data are spar...
arXiv:2610.19945v1 Announce Type: new Abstract: Within the most recent two decades, machine translation (MT) has been advanced from a research area to a mature, deployed technology for prose text and...
arXiv:2411.18954v5 Announce Type: replace-cross Abstract: Maximum a posteriori inference in a finite Markov random field is generally NP-hard. We study an instance-wise optimizer that minimizes the e...
arXiv:2610.14487v1 Announce Type: new Abstract: Generative recommendation models based on autoregressive decoding have been adopted as alternatives to classical ranking-based systems. While their mod...
arXiv:2610.14495v1 Announce Type: new Abstract: Explainer videos -- a worked geometry problem, why the sky is blue, how a dynasty fell -- are usually one more target for pixel video generation. We ar...
arXiv:2609.32717v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) alignment is intended to ensure that models remain helpful and safe, but its stability under input distributional...
arXiv:2610.15218v1 Announce Type: new Abstract: A recurrent-depth language model reuses one block of weights several times in a row. The number of repetitions, which we call loops, is chosen when the...
arXiv:2610.15221v1 Announce Type: new Abstract: AI agents can evolve by using environment feedback to revise their harnesses, the software managing model inputs, tool use, memory, and execution, whil...