Multi-Objective Coverage via Constraint Active Search
arXiv:2602.15595v1 Announce Type: new Abstract: In this paper, we formulate the new multi-objective coverage (MOC) problem where our goal is to identify a small set of representative samples whose predicted outcomes broadly cover the feasible multi-objective space. This problem is...
Certified Per-Instance Unlearning Using Individual Sensitivity Bounds
arXiv:2602.15602v1 Announce Type: new Abstract: Certified machine unlearning can be achieved via noise injection leading to differential privacy guarantees, where noise is calibrated to worst-case sensitivity. Such conservative calibration often results in performance degradation, limiting practical applicability. In this work,...
The Computer Vision Foundation – A non-profit organization that fosters and supports research in all aspects of computer vision
Join the Largest Global Community in Computing
IEEE Computer Society is the top source for information, inspiration, and collaboration in computer science and engineering, empowering technologist worldwide
Knowing When Not to Answer: Abstention-Aware Scientific Reasoning
arXiv:2602.14189v1 Announce Type: new Abstract: Large language models are increasingly used to answer and verify scientific claims, yet existing evaluations typically assume that a model must always produce a definitive answer. In scientific settings, however, unsupported or uncertain conclusions can...
Accelerated Discovery of Cryoprotectant Cocktails via Multi-Objective Bayesian Optimization
arXiv:2602.13398v1 Announce Type: new Abstract: Designing cryoprotectant agent (CPA) cocktails for vitrification is challenging because formulations must be concentrated enough to suppress ice formation yet non-toxic enough to preserve cell viability. This tradeoff creates a large, multi-objective design space in...
Comparing Classifiers: A Case Study Using PyCM
arXiv:2602.13482v1 Announce Type: new Abstract: Selecting an optimal classification model requires a robust and comprehensive understanding of the performance of the model. This paper provides a tutorial on the PyCM library, demonstrating its utility in conducting deep-dive evaluations of multi-class...
Finding Highly Interpretable Prompt-Specific Circuits in Language Models
arXiv:2602.13483v1 Announce Type: new Abstract: Understanding the internal circuits that language models use to solve tasks remains a central challenge in mechanistic interpretability. Most prior work identifies circuits at the task level by averaging across many prompts, implicitly assuming a...
Singular Vectors of Attention Heads Align with Features
arXiv:2602.13524v1 Announce Type: new Abstract: Identifying feature representations in language models is a central task in mechanistic interpretability. Several recent studies have made an implicit assumption that feature representations can be inferred in some cases from singular vectors of attention...
On Representation Redundancy in Large-Scale Instruction Tuning Data Selection
arXiv:2602.13773v1 Announce Type: new Abstract: Data quality is a crucial factor in large language models training. While prior work has shown that models trained on smaller, high-quality datasets can outperform those trained on much larger but noisy or low-quality corpora,...
Cast-R1: Learning Tool-Augmented Sequential Decision Policies for Time Series Forecasting
arXiv:2602.13802v1 Announce Type: new Abstract: Time series forecasting has long been dominated by model-centric approaches that formulate prediction as a single-pass mapping from historical observations to future values. Despite recent progress, such formulations often struggle in complex and evolving settings,...
Testing For Distribution Shifts with Conditional Conformal Test Martingales
arXiv:2602.13848v1 Announce Type: new Abstract: We propose a sequential test for detecting arbitrary distribution shifts that allows conformal test martingales (CTMs) to work under a fixed, reference-conditional setting. Existing CTM detectors construct test martingales by continually growing a reference set...