Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2608. 01298v1 Announce Type: cross Abstract: Diffusion Transformers (DiTs) have emerged as a core architecture in generative modeling due to their scalability and adaptability to multimodal tasks.
arXiv:2608. 01804v1 Announce Type: new Abstract: Post-training large language models (LLMs) via reinforcement learning (RL) has significantly advanced code generation capabilities.
arXiv:2608. 02070v1 Announce Type: cross Abstract: Brain-computer interfaces (BCIs) have been widely used in motor rehabilitation, disease diagnosis, and other neural engineering scenarios.
arXiv:2608. 02539v1 Announce Type: cross Abstract: We present a simple Gaussian approximation to the finite-sample distribution of the classical ridge regression estimator.
arXiv:2504. 06407v2 Announce Type: replace Abstract: Machine Unlearning aims to remove undesired information from trained models without full retraining from scratch.
arXiv:2603. 25062v2 Announce Type: replace Abstract: Autoregressive molecular models assign probability to molecular serializations even though chemical identity is invariant to serialization.
arXiv:2605. 28149v2 Announce Type: replace Abstract: Sparse Autoencoders (SAEs) extract interpretable features from Large Language Model activations, but standard variants enforce non-negative latents, so a bidirectional semantic axis (e.
arXiv:2410. 23212v3 Announce Type: replace-cross Abstract: In graph-based data analysis, $k$-nearest neighbor ($k$NN) graphs are widely used due to their adaptivity to local data densities.
arXiv:2511. 00382v2 Announce Type: replace-cross Abstract: Organizations increasingly adapt Large Language Models (LLMs) from public repositories such as HuggingFace to downstream tasks.
arXiv:2511. 12840v2 Announce Type: replace-cross Abstract: Overparameterized models often generalize well even when they interpolate noisy training data.
arXiv:2603. 24742v2 Announce Type: replace-cross Abstract: As the capabilities and adoption of Artificial Intelligence (AI) systems grow, trust in these AI systems is an increasingly urgent concern.
arXiv:2608. 00935v1 Announce Type: new Abstract: Electronic Health Records (EHRs) are widely used for clinical risk prediction using machine learning.
arXiv:2608. 01069v1 Announce Type: new Abstract: Bandit algorithms generate data for downstream inference, but adaptive sampling biases post-bandit sample means.
arXiv:2608. 00315v1 Announce Type: cross Abstract: Robot policies are becoming increasingly general, with vision-language-action (VLA) models enabling a single policy to execute diverse tasks specified in natural language.
arXiv:2608. 01032v1 Announce Type: new Abstract: Training error is what we can observe on a training set; test error is the quantity we actually care about.
arXiv:2608. 00978v1 Announce Type: new Abstract: Flow Matching trains continuous-time generative models by regressing the velocity field of a probability path between a simple source distribution and a target data distribution.
arXiv:2606. 15240v2 Announce Type: replace Abstract: Accurate vessel trajectory forecasting is essential for maritime situational awareness, navigation safety, traffic management, and autonomous navigation.
arXiv:2608. 00566v1 Announce Type: new Abstract: Post-hoc model explainers such as LIME, SHAP, and Integrated Gradients are widely deployed to audit models in high-stakes sensitive domains, including finance, healthcare, and social welfare.
arXiv:2608. 00301v1 Announce Type: new Abstract: Error-penalized scoring rules ($+1$ for a correct answer, $-\lambda$ for a wrong one, $0$ for abstaining) are increasingly prescribed against hallucination: a rational agent facing such a rule answers exactly when its correctness probability exceeds Chow's threshold $t^\ast=\lambda/(1+\lambda)$.
arXiv:2602. 13362v2 Announce Type: replace-cross Abstract: A key challenge in probabilistic regression is ensuring that predictive distributions accurately reflect true empirical uncertainty.