Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2609.39839v1 Announce Type: new Abstract: Class-Incremental Learning (CIL) aims to continuously learn new classes without forgetting previously acquired knowledge. Parameter-efficient fine-tuni...
arXiv:2609.40193v1 Announce Type: new Abstract: We establish near-linear accuracy bounds for the classical Moreau--Yosida unadjusted Langevin algorithm (MYULA). The target is $\pi\propto e^{-f-g}$, w...
arXiv:2609.40335v1 Announce Type: new Abstract: Differentially Private Stochastic Gradient Descent (DP-SGD) is a leading approach for privacy-preserving fine-tuning of large language models (LLMs). M...
arXiv:2609.38561v1 Announce Type: cross Abstract: Zeroth-order optimization methods are essential for solving black-box problems where gradient information is unavailable or expensive to compute. Thi...
arXiv:2609.38934v1 Announce Type: cross Abstract: Differentially private (DP) text generation can protect individual records, but privacy alone does not specify what evidence a released statement car...
arXiv:2609.39162v1 Announce Type: cross Abstract: Speaker diarization systems based on speaker embeddings and neural diarization exploit complementary forms of speaker information, but their intermed...
arXiv:2609.39531v1 Announce Type: cross Abstract: We study the problem of estimating the guidance that steers the distribution learned by a diffusion generative model toward a tilted target $q_0 \pro...
arXiv:2609.39552v1 Announce Type: cross Abstract: Text-to-song generation models can be prompted to imitate specific artists or regurgitate entire songs from their training data. Although these pheno...
arXiv:2609.39584v1 Announce Type: cross Abstract: Edge computing has emerged as a critical computing paradigm in modern distributed systems by migrating data processing closer to end users and Intern...
arXiv:2609.39768v1 Announce Type: cross Abstract: Certifying a deployed neural network raises decision problems that the verification literature has not classified: whether the model carries a backdo...
arXiv:2406.02447v5 Announce Type: replace Abstract: Federated Learning (FL) aims at unburdening the training of deep models by distributing computation across multiple devices (clients) while safegua...
arXiv:2601.22028v2 Announce Type: replace Abstract: Most LLM unlearning methods aim to approximate retrain-from-scratch behaviors with minimal distribution shift, often via alignment-style objectives...
arXiv:2605.16339v2 Announce Type: replace Abstract: Preference learning in large language models relies on reward models as proxies for human judgment. However, these models frequently exhibit prefer...
arXiv:2605.21617v3 Announce Type: replace Abstract: Locating genomic features from genomic contact maps, such as centromere identification from genome-wide chromosome conformation capture techniques,...
arXiv:2609.32322v2 Announce Type: replace Abstract: World models are typically trained and evaluated by prediction error, assuming that more accurate predictions lead to better decisions. We show tha...
arXiv:2609.32503v2 Announce Type: replace Abstract: Kolmogorov-Arnold Networks (KANs) are motivated in part by interpretability: their learned edge functions can be inspected, pruned, and reduced to...
arXiv:2602.06700v2 Announce Type: replace-cross Abstract: Graph-structured data underpin a wide spectrum of modern applications, yet their multiple sensitive attributes are not isolated but deeply co...
arXiv:2605.12890v2 Announce Type: replace-cross Abstract: The rapid advancement of large language models (LLMs) has made machine-generated text increasingly difficult to distinguish from human-writte...
arXiv:2606.20811v2 Announce Type: replace-cross Abstract: We study the problem of system identification in heterogeneous settings, where different systems may follow distinct underlying dynamics. Exi...
arXiv:2610.00319v1 Announce Type: new Abstract: Collaborative perception enables connected agents to share complementary observations for 3D object detection, extending sensing range and mitigating o...