Apple Workshop on Privacy-Preserving Machine Learning: Private Federated Learning (PFL) framework
AuthorsMona Chitnis (Apple), Filip Granqvist (Apple)
Apple Workshop on Privacy-Preserving Machine Learning: Private Federated Learning (PFL) framework
AuthorsMona Chitnis (Apple), Filip Granqvist (Apple)
Split-and-Scale Latent 3D Representations
November 16, 2026research area Computer Visionconference NeurIPS
Latent 3D representations have significantly expanded the capabilities of modern shape modeling, enabling compact encoding of 3D scenes and supporting powerful 3D generative models. Despite this progress, current representations struggle to capture the fine details of complex objects, fundamentally limited by the capacity of their latents. However, scaling latent capacity at training time is computationally expensive and often infeasible under…
Theoretical Limits of Language Model Alignment
November 12, 2026research area Fairness, research area Methods and Algorithmsconference NeurIPS
Language model (LM) alignment improves model outputs to reflect human preferences while preserving the capabilities of the base model. The most common alignment approaches are (i) reinforcement learning, which maximizes the expected reward under a KL-divergence constraint, and (ii) best-of- alignment, which selects the highest-reward output among independent samples. Despite their widespread use, the fundamental limits of reward…