Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
Ultrasound image classification is essential for computer-aided diagnosis. However, current methods often neglect clinical priors, leading to poor generalization in challenging scenarios and a lack of interpretability that limits clinical adoption.
Counterfactual explanation (CE) is widely used to enhance the interpretability of machine learning models and support data-driven decision-making based on model predictions. However, existing CE methods typically require two exogenously specified inputs: a desired output value (target) and a distance function that quantifies changes in explanatory variables.
Large language models are increasingly used as open-ended search operators in evolutionary optimization. We introduce Evolutionary Feature Engineering (EFE), a framework for using LLM-based evolution to discover preprocessing transformations for structured data.
Aligning large language models with diverse and heterogeneous human values requires multi-objective alignment methods to effectively trade off conflicting preference dimensions. Current methods achieve this trade-off by training policies conditioned on preference vectors and leveraging online direct preference optimization.
Large language models (LLMs) are increasingly used to generate queries, invoke tools, and construct analytical workflows. Although recent advances have substantially improved workflow generation and execution, the semantic information required to operationalize analytical concepts often lies beyond what is explicitly represented in database schemas and data values.
Congratulations to the Berkeley Artificial Intelligence Research (BAIR) Lab class of 2026! This year, BAIR celebrates another remarkable group of Ph.
Automated pathology report generation from Whole Slide Images (WSIs) has attracted increasing attention in digital pathology. However, existing methods are predominantly developed under single-organ settings, overlooking the multi-organ scenarios encountered in clinical practice, where organ types typically follow a long-tailed distribution.
Medical image segmentation relies on the ability of encoder-decoder architectures to translate rich feature representations into accurate pixel-level predictions under challenging conditions such as low contrast, structural ambiguity, and scale variability. While recent advances in large-scale pretraining and transformer-based encoders have substantially improved feature extraction, segmentation accuracy remains constrained by decoder design, particularly in terms of cross-scale alignment, contextual integration, and boundary preservation.
arXiv:2606. 31524v1 Announce Type: cross Abstract: The Self-Improving Alignment (SAIL) algorithm addresses distribution shift by reducing a bilevel formulation of the problem to an efficient, single-level method.
arXiv:2606. 31719v1 Announce Type: cross Abstract: In collaborative dialogue, shared perception does not guarantee shared interpretation.
arXiv:2606. 31973v1 Announce Type: cross Abstract: Semantic communication (SemCom) has emerged as a promising paradigm in which the transmission of task-relevant information is prioritized over raw data, enabling efficient and robust communication under resource and channel constraints.
arXiv:2606. 31480v1 Announce Type: new Abstract: We study constrained online convex optimization with adversarial losses and stochastic or adversarial constraints.
arXiv:2606. 31804v1 Announce Type: new Abstract: Accurate energy demand forecasting is essential for the reliable operation and planning of modern sustainable energy systems.
arXiv:2606. 31325v1 Announce Type: new Abstract: We present HistoriQA-ThirdRepublic: a French-language dataset of multi-hop historical questions derived from parliamentary debates and newspapers of the French Third Republic.
arXiv:2509. 15443v2 Announce Type: replace-cross Abstract: Human-to-humanoid imitation learning presents a promising pathway to address the severe data scarcity bottleneck in robotics by utilizing abundant, large-scale human motion collections.
arXiv:2606. 31536v1 Announce Type: new Abstract: As Quantum Machine Learning (QML) transitions toward practical implementation, the field faces a critical architectural bottleneck that challenges the fundamental assumptions of classical statistical learning theory.
arXiv:2606. 30836v1 Announce Type: new Abstract: Explainability in Many-Objective Optimization (MaO) is currently hindered by the escalating complexity of the Pareto front, which renders the relationship between high-dimensional decision variables and objective outcomes increasingly opaque.
arXiv:2606. 30788v1 Announce Type: new Abstract: Language models are often adapted in stages: a public skill phase, a private memory phase, and a later safety phase that learns to refuse outputs tied to the remembered entities.
arXiv:2606. 31420v1 Announce Type: new Abstract: Test-Time Adaptation (TTA) enables models trained on a source domain to adapt online to unlabeled test data under distribution shifts.
arXiv:2606. 31984v1 Announce Type: cross Abstract: Industrial recommendation systems serve billions of users through a multi-stage funnel -- retrieval, early-stage ranking, and re-ranking -- where the final re-ranking step disproportionately shapes user engagement and downstream performance, particularly for carousel and grid display formats.