Machine unlearning, which enables a model to forget specific data, is crucial for ensuring data privacy and model reliability. However, its effectiveness can be severely undermined in real-world scenarios where models learn unintended biases from spurious correlations within the data. This paper investigates the unique challenges of unlearning from such biased models. We identify a novel phenomenon we term “shortcut unlearning," where models exhibit an “easy to learn, yet hard to forget" tendency. Specifically, models struggle to forget […]

Ver mais

Earlier on Friday, the Trump administration used a rare “supply-chain security risk” designation to effectively ban U.S. military contractors from doing business with Anthropic, the second-largest AI startup in the world. This follows from a terse statement by Anthropic CEO Dario Amodei in which he reported the Administration’s requests for Anthropic to erase certain clauses from its contracts with the U.S. government—namely, contracts that would prevent domestic surveillance and use for fully autonomous weapons. In the aftermath of the […]

Ver mais

arXiv:2601.06296v2 Announce Type: replace-cross Abstract: A targeted learning (TL) framework is developed to estimate the difference in the restricted mean survival time (RMST) for a clinical trial with time-to-event outcomes. The approach starts by defining the target estimand as the RMST difference between investigational and control treatments. Next, an efficient estimation method is introduced: a targeted minimum loss estimator (TMLE) utilizing pseudo-observations. Moreover, a version of the copy reference (CR) approach is developed to perform a sensitivity analysis […]

Ver mais

A paper from our group was accepted to an ICCV25 workshop. Copyright transfer was completed, registration was completed, and the paper was presented at the workshop. In 2026 March (by random chance) we found out that it never appeared in the proceedings. We asked the ICCV workshop group about it, and they simply stated that the paper had been removed because it was “not registered.” But it was registered, and we have documentation for that. No explanation was […]

Ver mais

arXiv:2601.12284v1 Announce Type: new Abstract: The rapid evolution of the automobile sector, driven by advancements in connected and autonomous vehicles (CAVs), has transformed how vehicles communicate, operate, and interact with their surroundings. Technologies such as Vehicle-to-Everything (V2X) communication enable autonomous cars to generate and exchange substantial amounts of data with real-world entities, enhancing safety, improving performance, and delivering personalized user experiences. However, this data-driven ecosystem introduces significant challenges, particularly concerning data privacy, security, and governance. The absence of […]

Ver mais

arXiv:2603.23835v1 Announce Type: new Abstract: There remain theoretical gaps in deep neural network estimators for the nonparametric Cox proportional hazards model. In particular, it is unclear how gradient-based optimization error propagates to population risk under partial likelihood, how pointwise bias can be controlled to permit valid inference, and how ensemble-based uncertainty quantification behaves under realistic variance decay regimes. We develop an asymptotic distribution theory for deep Cox estimators that addresses these issues. First, we establish nonasymptotic oracle inequalities […]

Ver mais

arXiv:2602.09269v1 Announce Type: new Abstract: Inclusion, equity, and access are widely valued in AI and education, yet are often assessed through coarse sample descriptors or post-hoc self-reports that miss how inclusion is shaped moment by moment in collaborative problem solving (CPS). In this proof-of-concept paper, we introduce inclusion analytics, a discourse-based framework for examining inclusion as a dynamic, interactional process in CPS. We conceptualize inclusion along three complementary dimensions — participation equity, affective climate, and epistemic equity — […]

Ver mais

Many approximate machine unlearning methods demonstrate strong logit-level forgetting — such as near-zero accuracy on the forget set — yet continue to preserve substantial information within their internal feature representations. We refer to this discrepancy as superficial forgetting. Recent studies indicate that most existing unlearning approaches primarily alter the final classifier, leaving intermediate representations largely unchanged and highly similar to those of the original model. To address this limitation, we introduce the Erase at the Core (EC), a […]

Ver mais

arXiv:2312.10424v4 Announce Type: replace-cross Abstract: We derive uniform all-time concentration bound of the type ‘for all $n geq n_0$ for some $n_0$’ for TD(0) with linear function approximation. We work with online TD learning with samples from a single sample path of the underlying Markov chain. This makes our analysis significantly different from offline TD learning or TD learning with access to independent samples from the stationary distribution of the Markov chain. We treat TD(0) as a contractive […]

Ver mais