arXiv:2512. 18390v2 Announce Type: replace Abstract: Organizations often have an incumbent predictive model in production when new data sources become available.
arXiv:2605. 16430v2 Announce Type: replace-cross Abstract: Scaling LLMs requires tremendous computational resources, and recent advances in AI have gone hand in hand with massive amounts of capital expenditure.
arXiv:2607. 10694v1 Announce Type: cross Abstract: We study the problem of optimal continual fine-tuning for a pre-trained Foundation Model deployed at a resource-limited device.
arXiv:2605. 26919v2 Announce Type: replace Abstract: Maintaining predictive accuracy in non-stationary environments requires online model selection to adapt autonomously to unknown distribution shifts.
arXiv:2606. 30852v1 Announce Type: new Abstract: Reasoning models spend different amounts of useful computation across instances, but it remains unclear when a learned stopping rule improves over simple confidence or convergence thresholds.
arXiv:2609.00710v1 Announce Type: cross Abstract: An LLM application often sells or internally allocates several service products: a small or premium model, a short or long token cap, and possibly mu...
arXiv:2607. 11653v1 Announce Type: new Abstract: Black-box conditional quantile forecasts are widely used for sequential decisions under asymmetric costs, such as inventory planning in supply chain management.
The paper presents a new scaling law for reward optimization in AI alignment, showing that performance scales as Θ(√min{log(M), K}), where M is the number of preference comparisons used to train a proxy reward model and K is the KL‑divergence budget relative to a reference policy. The authors derive this law using an information‑theoretic model, prove its tightness, and validate it with extensive experiments involving a 70B gold reward model and smaller proxy models (0.6B–4B). The empirical results demonstrate a strong fit (R² 97–99 %) across different model sizes, noise levels, and optimization methods, suggesting that reward optimization behaves like a simple selection task over IID Gaussian variables with noisy feedback.
Rolling Conformal Prediction (rolling‑CP) is a distribution‑free predictive inference method designed for sequential model training. It calibrates each incoming observation against the current predictor and incorporates it into future training, eliminating the need for data splitting. For exchangeable data, rolling‑CP guarantees marginal coverage with a universal factor‑two bound, and for i.i.d. streams it provides high‑probability training‑conditional validity over time, improving to the target level under stability conditions.
arXiv:2602. 06136v2 Announce Type: replace Abstract: Test-time adaptation (TTA) offers a compelling remedy for machine learning (ML) models that degrade under domain shifts, improving generalisation on-the-fly with only unlabelled samples.
arXiv:2608. 02845v1 Announce Type: new Abstract: Tabular model performance degrades when feature distributions change over time or the relationship between features and outcome variables change over time, known as data drift and concept drift, respectively.
arXiv:2509. 22992v2 Announce Type: replace Abstract: As machine learning models continue to grow in size and complexity, efficient serving faces increasingly broad trade-offs spanning accuracy, latency, resource usage, and other objectives.
arXiv:2608. 19488v1 Announce Type: new Abstract: Production machine learning systems degrade under concept drift, yet practitioners have little principled guidance on when to retrain.