New scaling laws optimize model size, training, and inference for better performance.
problem Trade-off between model size and inference cost in modern LLMs.
method Train-to-Test (T2) scaling laws that jointly optimize model size, training tokens, and inference samples. result Optimal pretraining decisions shift into overtraining regime, leading to stronger performance.
The abstract explores connections between reinforcement learning, scaling, and diffusion.
problem Aligning reinforcement learning with human feedback and scaling techniques.
method Clarifying connections between reinforcement learning, scaling, and diffusion.
result Introducing a resampling approach for alignment and reward-directed diffusion models.
The study examines how verifier imperfections impact test-time scaling techniques.
problem Understanding how verifier imperfections affect test-time scaling methods.
method Proves the instance-level accuracy of Best-of-N and Rejection Sampling methods using the geometry of the verifier's ROC curve.
result RS outperforms BoN for fixed compute, but both converge to the same accuracy in the infinite-compute limit.
The study examines how extra compute during testing affects the performance of large language models.
problem Understanding the conditions under which test-time scaling improves model performance.
method An in-context weight prediction task for linear regression was used to train transformers. The performance was analyzed under varying levels of test-time compute.
result Training transformers on diverse, relevant, and hard tasks leads to the best performance for test-time scaling.
This work explores test-time scaling strategies for LLMs, improving sample efficiency and expressiveness.
problem Understanding the sample efficiency and expressiveness of test-time scaling strategies for LLMs.
method Established separation and expressiveness results for self-consistency, best-of-n, and self-correction strategies. result Self-correction enables Transformers to simulate online learning over multiple tasks without prior knowledge.
New method predicts and optimizes test-time scaling for LLMs.
problem Lack of principled guidance on scaling LLMs efficiently.
method Tail-guided search to predict and allocate compute.
result SLG Search achieves higher rewards with less compute.
Implicit models can match or exceed explicit models with more test-time compute.
problem Understanding the expressive power and scaling of implicit models.
method Nonparametric analysis of expressive power, mathematical characterization of implicit operators, and test-time scaling experiments.
result Implicit models can progressively express more complex mappings through iteration, matching a richer function class with test-time compute.
QAlign improves language model alignment with less compute, outperforming existing methods.
problem Improving language model performance with limited test-time computation.
method QAlign: sampling from optimal aligned distribution using Markov chain Monte Carlo.
result Consistent improvements over existing methods on various benchmarks.
Adaptive compute allocation improves model performance by prioritizing harder queries.
problem Inefficiency in allocating test-time compute uniformly across all queries.
method Formulated as a bandit learning problem, proposed adaptive algorithms that estimate query difficulty and allocate compute accordingly.
result Achieved up to 15.29% relative performance improvement on various benchmarks.
We introduce online learning algorithms which are independent of feature scales, proving regret bounds dependent on the ratio of scales existent in the data rather than the absolute scale. This has several useful effects: there is no need to pre-normalize data, the test-time and test-space complexity are reduced, and t…
We introduce online learning algorithms which are independent of feature scales, proving regret bounds dependent on the ratio of scales existent in the data rather than the absolute scale. This has several useful effects: there is no need to pre-normalize data, the test-time and test-space complexity are reduced, and t…
Duel-Evolve uses LLM self-preferences for test-time optimization of discrete outputs.
problem Optimizing LLM outputs at test time with limited or unreliable scalar rewards.
method Duel-Evolve uses pairwise comparisons from the LLM to guide optimization, aggregating them via a Bayesian Bradley-Terry model.
result Achieves significant improvement over existing methods in accuracy.
New method optimizes language model performance for test-time strategies.
problem Mismatch between training objectives and test-time deployment of large language models.
method Tail-Extrapolated estimators to approximate best-of-N performance from limited training rollouts.
result Improved performance of best-of-N deployment across various models and datasets.
Recently, machine learning algorithms have successfully entered large-scale real-world industrial applications (e.g. search engines and email spam filters). Here, the CPU cost during test time must be budgeted and accounted for. In this paper, we address the challenge of balancing the test-time cost and the classifier …
Sampling more can make models more confident in wrong answers, not better.
problem The modal ceiling and correlation ceiling limit the benefit of increased sampling.
method Analyzes the trade-offs between sampling more and selecting the best answer.
result Extra sampling beyond a certain point does not improve model performance and can even degrade it.
Paper proposes an efficient method for calibrating spatio-temporal forecasts.
problem Real-world spatio-temporal forecasting challenges like signal anomalies and distributional shifts.
method Learning with Calibration (ST-TTC) for real-time bias correction.
result ST-TTC improves spatio-temporal forecasting accuracy with reduced computational cost.
The safety and robustness of learning-based decision-making systems are under threats from adversarial examples, as imperceptible perturbations can mislead neural networks to completely different outputs. In this paper, we present an adaptive view of the issue via evaluating various test-time smoothing defense against …
Unified framework for certifying LLM reliability without extra supervision.
problem Improving reliability of large language models without additional supervision.
method Unified framework using majority voting and Martingale Majority Certificate (MMC).
result Certifiable inference in LLMs with statistical guarantees and adaptive stopping rules.
GSI improves efficiency of large language model inference.
problem Efficiently guiding test-time alignment in large language models.
method Combines soft best-of-n scaling with a reward model and speculative samples. result Achieves higher accuracy and reduced latency compared to standard methods.
ORCA calibrates LLMs for efficient, generalizable reasoning.
problem Miscalibration of large language models leading to inefficiencies.
method Online Reasoning Calibration (ORCA) using conformal prediction and test-time training.
result ORCA provides higher efficiency and generalization across different reasoning tasks.
Study compares data-driven vs model-based MRS quantification strategies, focusing on resilience to out-of-distribution effects.
problem Resilience to out-of-distribution effects in data-driven MRS quantification.
method Compared three data-driven strategies (supervised regression, self-supervised learning, test-time adaptation) against model-based fitting tools.
result Test-time adaptation proved most resilient to out-of-distribution effects, while self-supervised learning achieved intermediate performance.
PRISM infers model structures and parameters from simulations, controlling complexity at test time.
problem Choosing among large model families for scientific discovery.
method Simulation-based encoder-decoder that infers model structures and parameters, with test-time complexity control.
result PRISM scales to large model families and performs model selection in biophysical diffusion MRI.
Improves generative models by optimizing rewards and sample editing.
problem Efficiently generating high-reward samples with structural constraints.
method Introduces MDM-VGB, a discrete diffusion sampler that augments unmasking generation with reward-guided remasking.
result MDM-VGB achieves quadratic complexity and robustness to noise, outperforming heuristics like best-of-N. This paper improves test-time adaptation for distribution shifts using confidence maximization and input transformation.
problem Improving deep networks' performance on data shifted from the training distribution.
method Proposes a novel loss function combining confidence maximization and batch-wise entropy maximization with an input transformation module.
result Significantly improves robustness of pretrained networks to corruptions on benchmarks like ImageNet-C.
A probabilistic framework for online test-time adaptation
problem Adapting models to new data under distributional shift
method State-space modelling architecture
result Characterizing parameter learning, time evolution, prior tuning, and prediction
Test-time data augmentation−averaging the predictions of a machine learning model across multiple augmented samples of data−is a widely used technique that improves the predictive performance. While many advanced learnable data augmentation techniques have emerged in recent years, they are focused on the training p…
Risk monitoring detects when TTA models degrade at test time.
problem Detecting when TTA models degrade at test time.
method Extended risk monitoring tools based on sequential testing with confidence sequences.
result Demonstrated effectiveness of TTA monitoring framework across various datasets and methods.
Study reveals how depth of reasoning affects generalization in models.
problem Understanding scaling behavior of generalization with CoT depth.
method Theoretical model of CoT in linear regression using random matrix theory.
result Sharp phase transition between exponential and polynomial improvement, saturation, and overthinking.
Meta-SAGE improves deep RL scalability for CO tasks by adapting pre-trained models to larger-scale problems.
problem Improving scalability of deep reinforcement learning models for combinatorial optimization tasks.
method Meta-SAGE combines a scale meta-learner and scheduled adaptation with guided exploration to adjust model parameters for larger-scale problems.
result Meta-SAGE outperforms previous methods and significantly improves scalability in CO tasks.
Improves diffusion model performance and efficiency through classical search.
problem Tackles inference-time control in diffusion models.
method Proposes a framework combining local and global search for efficient navigation.
result Significant gains in performance and efficiency across various domains.
RG-TTA adapts neural forecasters to streaming time series shifts by modulating adaptation intensity.
problem Adapting neural forecasters to distribution shifts in streaming time series data.
method RG-TTA uses a meta-controller that continuously modulates adaptation intensity based on distributional similarity.
result RG-TTA achieves the lowest MSE in 156 of 224 seed-averaged experiments, reducing MSE by 5.7% vs TTA.
We show that several popular few-shot learning benchmarks can be solved with varying degrees of success without using support set Labels at Test-time (LT). To this end, we introduce a new baseline called Centroid Networks, a modification of Prototypical Networks in which the support set labels are hidden from the metho…
VCoTTA uses variational Bayesian methods to adapt models under continuous domain shifts.
problem Error accumulation in continual test-time adaptation.
method VCoTTA employs variational Bayesian techniques to update a Bayesian Neural Network (BNN) during testing, combining priors from source and teacher models.
result VCoTTA effectively mitigates error accumulation in CTTA, as shown by experimental results on three datasets.
A significant advance in accelerating neural network training has been the development of normalization methods, permitting the training of deep models both faster and with better accuracy. These advances come with practical challenges: for instance, batch normalization ties the prediction of individual examples with o…
We conduct a large-scale study of language models for chord prediction. Specifically, we compare N-gram models to various flavours of recurrent neural networks on a comprehensive dataset comprising all publicly available datasets of annotated chords known to us. This large amount of data allows us to systematically exp…
CPATTA uses conformal prediction for efficient test-time adaptation.
problem Low data selection efficiency in existing ATTA methods.
method Conformal Prediction, online weight-update algorithm, domain-shift detector, staged update scheme.
result CPATTA consistently outperforms state-of-the-art methods by 5% in accuracy.
Paper tackles test-time adaptation for tabular data.
problem Performance degradation due to distribution shifts in testing.
method Proposes FTAT for robustly adapting tabular models during testing.
result FTAT outperforms state-of-the-art methods on benchmark datasets.
This paper addresses detection of a reverse engineering (RE) attack targeting a deep neural network (DNN) image classifier; by querying, RE's aim is to discover the classifier's decision rule. RE can enable test-time evasion attacks, which require knowledge of the classifier. Recently, we proposed a quite effective app…
Machine learning models are often used at test-time subject to constraints and trade-offs not present at training-time. For example, a computer vision model operating on an embedded device may need to perform real-time inference, or a translation model operating on a cell phone may wish to bound its average compute tim…
Sloth predicts LLM performance using latent skills across families.
problem Variations in benchmark performance due to differences in training configurations and data processing across model families.
method Sloth uses publicly available benchmark data and assumes LLM performance is driven by latent skills influenced by model size and training tokens. It exploits correlations across benchmarks to provide accurate predictions.
result Sloth predicts LLM performance accurately and offers insights into scaling behaviors for complex tasks.
Enhances image quality to improve test-time adaptation accuracy.
problem Reducing accuracy loss due to distribution shift in deep networks.
method Integrates image enhancement with TTA methods to reduce prediction uncertainty.
result TECA method increases accuracy of TTA methods without hyperparameters.
A new approach for test-time adaptation detects and reacts to distribution shifts.
problem Improving test-time accuracy under distribution shifts.
method Online self-training with a detection tool based on entropy values and betting martingales.
result The classifier's entropy values match those of the source domain, building invariance to distribution shifts.
DAD++ improves test-time adversarial defense without access to training data.
problem Improving adversarial robustness of pre-trained models without access to training data.
method Test-time Data-free Adversarial Defense (DAD++) with detection and correction schemes.
result DAD++ significantly improves adversarial robustness with minimal clean accuracy drop.
Convolutional neural networks (CNNs) are commonly trained using a fixed spatial image size predetermined for a given model. Although trained on images of aspecific size, it is well established that CNNs can be used to evaluate a wide range of image sizes at test time, by adjusting the size of intermediate feature maps.…
Tent adapts models during testing by minimizing entropy of predictions.
problem Adapting models to new data during testing with limited information.
method Test entropy minimization (tent) and online channel-wise affine transformations.
result Reduces generalization error on various datasets and benchmarks.
A-NeSI scales approximate inference for probabilistic neurosymbolic learning.
problem Combining neural networks with symbolic reasoning for scalable inference.
method A-NeSI: a new framework for PNL using neural networks for approximate inference.
result A-NeSI achieves scalable approximate inference without semantic changes.
Adapts CNN for robust medical image segmentation across different scanners and protocols.
problem Performance degradation of CNNs in medical image segmentation due to mismatch between training and test images.
method Designs a segmentation CNN as a concatenation of a shallow normalization CNN and a deep CNN. At test time, adapts the normalization sub-network for each test image using a denoising autoencoder.
result Consistently improves performance on multi-center MRI datasets of brain, heart, and prostate.
Unified framework for sequence models using test-time regression.
problem Designing efficient sequence models with associative memory.
method Formalizing associative recall as regression over input tokens, deriving various sequence models.
result Clarifies the effectiveness of query-key normalization in softmax attention and offers new generalizations.