arXiv Statistics ML
HIFI: A Highly Efficient Framework for Statistical Inference with Foundation Models
Read the original on arXiv Statistics ML →The Flow has not summarised this story yet — read it at arXiv Statistics ML.
Related stories
arXiv AI
Sep 24
Fine-Tune, Then Rectify
The paper proposes a two‑stage framework that first fine‑tunes a large language model (LLM) and then rectifies its outputs, allocating limited labeled data optimally between the stages. It argues that the usual mean‑squared‑error objective for fine‑tuning misaligns with the downstream rectification, and instead suggests minimizing prediction‑error variance for mean estimation or a scalarized variance metric for general M‑estimation. Empirical results confirm that this variance‑based fine‑tuning, combined with optimal data allocation, yields significant efficiency gains over using either fine‑tuning or rectification alone, or using the conventional objective.
arXiv Machine Learning
Sep 7
Beyond Homoscedasticity: Decoupled Uncertainty Optimization for Deep Imbalanced Regression
The paper introduces DUO, a framework for Deep Imbalanced Regression that models each prediction as a conditional Gaussian to capture instance‑level uncertainty. By decoupling mean and variance optimization, DUO enhances learning signals for tail samples and mitigates gradient coupling that hampers hard examples. A distribution‑guided contrastive learning component further refines feature representations, leading to state‑of‑the‑art performance on several visual and biological regression benchmarks.
arXiv Machine Learning
Jun 25
Efficient Analytic Uncertainty Quantification for Multi-Modal Regression
arXiv:2606. 25188v1 Announce Type: new Abstract: Efficient uncertainty quantification (UQ) is essential for trustworthy large-scale learning.
arXiv AI
Sep 10
From Synthetic Priors to Model Behavior: Structural Coverage in Tabular Foundation Models
The paper investigates how synthetic pretraining priors used in tabular foundation models (TFMs) influence downstream performance. By reconstructing the synthetic data generators of four TFMs and comparing their generated tasks to two popular tabular benchmarks using structural descriptors, the authors measure structural coverage and normalized density. They find that some generators provide broader and denser support for benchmark tasks, and that stronger synthetic-to-benchmark support generally correlates with better model performance.
arXiv AI
6d ago
FOCUS: Benchmarking Retinal Model Generalization from Foundation Vision Encoders to Multimodal LLMs
The paper introduces FOCUS, a cross‑dataset benchmark for retinal fundus models that evaluates vision‑only encoders, vision‑language dual encoders, and multimodal large language models across ten public datasets. It measures ranking performance, calibration, subgroup disparities, and image‑quality robustness for tasks such as diabetic retinopathy and glaucomatous optic neuropathy. Results show no single model family dominates, with vision‑only encoders ranking highest on average, while fine‑tuning improves in‑domain performance but varies in external transfer.
arXiv Machine Learning
Jun 5
General Synthetic-Powered Inference
arXiv:2509. 20345v3 Announce Type: replace-cross Abstract: The rapid proliferation of high-quality synthetic data -- generated by advanced AI models or collected as auxiliary data from related tasks -- presents both opportunities and challenges for statistical inference.