Related papers: Probing Routing-Conditional Calibration in Attenti…
Post-hoc recalibration methods are widely used to ensure that classifiers provide faithful probability estimates. We argue that parametric recalibration functions based on logistic regression can be motivated from a simple theoretical…
At very high sparsity, neural network pruning does more than decide which weights remain. It also determines where pruning induced damage is placed across the network, and whether that damage can be recovered by a fixed lightweight repair…
Continuous monitoring of trained ML models to determine when their predictions should and should not be trusted is essential for their safe deployment. Such a framework ought to be high-performing, explainable, post-hoc and actionable. We…
Ride-hailing and autonomous mobility-on-demand operators reposition idle supply before future demand is fully observed. We study a retrieval-calibrated predict-then-optimize approach for this problem: historical demand regimes are matched…
The prediction accuracy of machine learning methods is steadily increasing, but the calibration of their uncertainty predictions poses a significant challenge. Numerous works focus on obtaining well-calibrated predictive models, but less is…
Modern end-to-end automatic speech recognition (ASR) models like Whisper not only suffer from reduced recognition accuracy in noise, but also exhibit overconfidence - assigning high confidence to wrong predictions. We conduct a systematic…
Robotic policies deployed in real-world environments often encounter post-training faults, where retraining, exploration, or system identification are impractical. We introduce an inference-time, cerebellar-inspired residual control…
Adversarial Training (AT) is one of the most effective methods for developing robust deep neural networks (DNNs). However, AT faces a trade-off problem between clean accuracy and adversarial robustness. In this work, we reveal a surprising…
A typical desideratum for quantifying the uncertainty from a classification model as a prediction set is class-conditional singleton set calibration. That is, such sets should map to the output of well-calibrated selective classifiers,…
Classical cluster inference is hampered by the spatial specificity paradox. Given the null-hypothesis of no active voxels, the alternative hypothesis states that there is at least one active voxel in a cluster. Hence, the larger the cluster…
Conventional optimization-based metering depends on strict adherence to precomputed schedules, which limits the flexibility required for the stochastic operations of Advanced Air Mobility (AAM). In contrast, multi-agent reinforcement…
We propose an evaluation framework for class probability estimates (CPEs) in the presence of label uncertainty, which is commonly observed as diagnosis disagreement between experts in the medical domain. We also formalize evaluation metrics…
Conformal prediction (CP) provides distribution-free, finite-sample coverage guarantees but critically relies on exchangeability, a condition often violated under distribution shift. We study the robustness of split conformal prediction…
We audit alignment-induced shifts in residual-stream activations of three open-weight instruction-tuned LLMs (Llama-3.1-8B-Instruct, Gemma-2-9B-it, Qwen-2.5-7B-Instruct) using the effective rank of the alignment modification matrix on…
Accurate and robust trajectory predictions of road users are needed to enable safe automated driving. To do this, machine learning models are often used, which can show erratic behavior when presented with previously unseen inputs. In this…
Post-hoc attribution methods aim to explain deep learning predictions by highlighting influential input pixels. However, these explanations are highly non-robust: small, imperceptible input perturbations can drastically alter the…
Proper confidence calibration of deep neural networks is essential for reliable predictions in safety-critical tasks. Miscalibration can lead to model over-confidence and/or under-confidence; i.e., the model's confidence in its prediction…
Recent years have witnessed significant progress in autonomous navigation using reinforcement learning. However, existing approaches largely emphasize reinforcement learning framework design, such as input representations, action spaces,…
Contact-rich micromanipulation in microfluidic flow is challenging because small disturbances can break pushing contact and induce large lateral drift. We study planar cell pushing with a magnetic rolling microrobot that tracks a…
Large language models are increasingly deployed in high-stakes tasks, where confident yet incorrect inferences may cause severe real-world harm, bringing the previously overlooked issue of confidence faithfulness back to the forefront. A…