Apple Workshop on Privacy-Preserving Machine Learning & AI 2026
At Apple, we believe privacy is a fundamental human right. As AI capabilities increase and become more integrated into people’s daily lives, advancing research in privacy-preserving techniques is increasingly important to ensure privacy is protected while users enjoy innovative AI experiences.
Appl...
Large-Scale High-Quality 3D Gaussian Head Reconstruction from Multi-View Captures
We propose HeadsUp, a scalable feed-forward method for reconstructing high-quality 3D Gaussian heads from large-scale multi-camera setups. Our method employs an efficient encoder-decoder architecture that compresses input views into a compact latent representation. This latent representation is then...
ANDRE: An Attention-based Neuro-symbolic Differentiable Rule Extractor
arXiv:2605.04193v1 Announce Type: new
Abstract: Inductive Logic Programming (ILP) aims to learn interpretable first-order rules from data, but existing symbolic and neuro-symbolic approaches struggle to scale to noisy and probabilistic settings. Classical ILP relies on discrete combinatorial rule s...
arXiv:2605.04100v1 Announce Type: new
Abstract: Off-policy temporal-difference (TD) learning with function approximation faces a structural tradeoff among stability, projection geometry, and variance control. Emphatic TD (ETD) improves the off-policy projection geometry through follow-on emphasis, ...
A Self-Attentive Meta-Optimizer with Group-Adaptive Learning Rates and Weight Decay
arXiv:2605.04055v1 Announce Type: new
Abstract: Adaptive optimizers like AdamW apply uniform hyperparameters across all parameter groups, ignoring heterogeneous optimization dynamics across layers and modules. We address this limitation by proposing MetaAdamW - a new optimizer that integrates a sel...
Text-Conditional JEPA for Learning Semantically Rich Visual Representations
Image-based Joint-Embedding Predictive Architecture (I-JEPA) offers a promising approach to visual self-supervised learning through masked feature prediction. However with the inherent visual uncertainty at masked positions, feature prediction remains challenging and may fail to learn semantic repre...
What Matters in Practical Learned Image Compression
One of the major differentiators unlocked by learned codecs relative to their hard-coded traditional counterparts is their ability to be optimized directly to appeal to the human visual system. Despite this potential, a perceptual yet practical image codec is yet to be proposed. In this work, we aim...
Making the Invisible Visible: Understanding the Mismatch Between Organizational Goals and Worker Experiences in AI Adoption
arXiv:2605.03078v1 Announce Type: new
Abstract: While AI is often introduced into organizations to drive innovation and efficiency, many adoption efforts fail as workers resist and struggle to integrate these systems. These failures point to a deeper issue: workers, the very people expected to coll...
Computing Thiele Rules on Interval Elections and their Generalizations
arXiv:2605.03067v1 Announce Type: new
Abstract: Approval-based committee voting has received significant attention in the social choice community. Among the studied rules, Thiele rules, and especially Proportional Approval Voting (PAV), stand out for desirable properties such as proportional repres...
arXiv:2605.02907v1 Announce Type: new
Abstract: Softmax attention maps every query--key interaction into a probability distribution, but the underlying structure remains largely unexplored. We define the \emph{energy field}, the row-centered attention logit, and show that it exhibits invariant prop...
SpecMD: A Comprehensive Study on Speculative Expert Prefetching
Mixture-of-Experts (MoE) models enable sparse expert activation, meaning that only a subset of the model’s parameters is used during each inference. However, to translate this sparsity into practical performance, an expert caching mechanism is required. Previous works have proposed hardware-centric ...
Accelerating battery research with an AI interface between FINALES and Kadi4Mat
arXiv:2605.00909v1 Announce Type: new
Abstract: The time-consuming formation process critically impacts the longevity of sodium-ion coin cells and End Of Life (EOL) performance. This study aims to optimize formation protocols for duration efficiency, targeting high-performance outcomes while minimi...
ClinicBot: A Guideline-Grounded Clinical Chatbot with Prioritized Evidence RAG and Verifiable Citations
arXiv:2605.00846v1 Announce Type: new
Abstract: Clinical diagnosis requires answers that are accurate, verifiable, and explicitly grounded in official guidelines. While large language models excel at natural language processing, their tendency to hallucinate undermines their utility in high-stakes ...
Sparse Regression under Correlation and Weak Signals: A Reproducible Benchmark of Classical and Bayesian Methods
arXiv:2605.00835v1 Announce Type: new
Abstract: Choosing between classical and Bayesian sparse regression methods involves a real trade-off: penalized estimators like Lasso run in milliseconds but give no uncertainty estimates,while Horseshoe and Spike-and-Slab priors produce full posteriors but ne...
Learning physically grounded traffic accident reconstruction from public accident reports
arXiv:2605.00050v1 Announce Type: new
Abstract: Traffic accidents are routinely documented in textual reports, yet physically grounded accident reconstruction remains difficult because detailed scene measurements and expert reconstructions are scarce, costly and hard to scale. Here we formulate acc...
FedACT: Concurrent Federated Intelligence across Heterogeneous Data Sources
arXiv:2605.00011v1 Announce Type: new
Abstract: Federated Learning (FL) enables collaborative intelligence across decentralized data source devices in a privacy-preserving way. While substantial research attention has been drawn to optimizing the learning process for an individual task, real-world ...
As artificial intelligence transforms society, Stanford HAI’s James Landay, Fei-Fei Li, and John Hennessy explain why they’re merging HAI with the Stanford Data Science initiative, mobilizing “team science at scale,” and betting that academic openness will shape AI’s future.
Stanford Merges AI and Data Science Efforts Under Single Institute
The combined institute will retain the Stanford HAI name and be helmed by computer scientist James Landay. Co-founder Fei-Fei Li takes on a new university-wide role as Special Advisor on AI and joins John Hennessy as co-chair of the advisory council.
Compositional Meta-Learning for Mitigating Task Heterogeneity in Physics-Informed Neural Networks
arXiv:2604.26999v1 Announce Type: new
Abstract: Physics-informed neural networks (PINNs) approximate solutions of partial differential equations (PDEs) by embedding physical laws into the loss function. In parameterized PDE families, variations in coefficients or boundary/initial conditions define ...
Automatic Causal Fairness Analysis with LLM-Generated Reporting
arXiv:2604.27011v1 Announce Type: new
Abstract: AutoML, intended as the process of automating the application of machine learning to real-world problems, is a key step for AI popularisation. Most AutoML frameworks are not accounting for the potential lack of fairness in the training data and in the...