arXiv:2510.06640v2 Announce Type: replace-cross Abstract: State Space Models (SSMs) have recently emerged as efficient alternatives to Transformer-Based Models (TBMs) for long-sequence processing with linear scaling, yet how contextual information flows across layers in these architectures remains understudied. We present the…
arXiv:2601.03420v1 Announce Type: new Abstract: As Large Language Models (LLMs) are increasingly deployed in safety-critical domains, rigorously evaluating their robustness against adversarial jailbreaks is essential. However, current safety evaluations often overestimate robustness because existing automated attacks are limited by restrictive…
arXiv:2601.03786v1 Announce Type: cross Abstract: Training data influence estimation methods quantify the contribution of training documents to a model’s output, making them a promising source of information for example-based explanations. As humans cannot interpret thousands of documents, only a small…
arXiv:2601.03424v1 Announce Type: new Abstract: Behavioral benchmarks tell us textit{what} a model does, but not textit{how}. We introduce a training-free mechanistic probe using attention-graph spectra. Treating each layer as a token graph, we compute algebraic connectivity ($lambda_2$), smoothness, and spectral…
arXiv:2601.03905v1 Announce Type: cross Abstract: Agents built on vision-language models increasingly face tasks that demand anticipating future states rather than relying on short-horizon reasoning. Generative world models offer a promising remedy: agents could use them as external simulators to foresee…
arXiv:2601.03425v1 Announce Type: new Abstract: Mixture of Experts models are widely assumed to achieve domain specialization through sparse routing. In this work, we question this assumption by introducing COMMITTEEAUDIT, a post hoc framework that analyzes routing behavior at the level…
arXiv:2601.04120v1 Announce Type: cross Abstract: Optimal control of obstacle problems arises in a wide range of applications and is computationally challenging due to its nonsmoothness, nonlinearity, and bilevel structure. Classical numerical approaches rely on mesh-based discretization and typically require solving…
arXiv:2601.03434v1 Announce Type: new Abstract: News videos are carefully edited multimodal narratives that combine narration, visuals, and external quotations into coherent storylines. In recent years, there have been significant advances in evaluating multimodal large language models (MLLMs) for news video…
arXiv:2308.08794v2 Announce Type: replace Abstract: Tipping points are abrupt, drastic, and often irreversible changes in the evolution of non-stationary and chaotic dynamical systems. For instance, increased greenhouse gas concentrations are predicted to lead to drastic decreases in low cloud cover,…
arXiv:2601.03450v1 Announce Type: new Abstract: User-Defined Text Classification (UDTC) considers the challenge of classifying input text to user-specified, previously unseen classes, a setting that arises frequently in real-world applications such as enterprise analytics, content moderation, and domain-specific information retrieval. We…
