Related papers: Adaptive Test-Time Compute Allocation with Evolvin…

Test-time scaling has become a powerful way to improve large language models. However, existing methods are best suited to short, bounded outputs that can be directly compared, ranked or refined. Long-horizon coding agents violate this…

Test-time training (TTT) methods explicitly update the weights of a model to adapt to the specific test instance, and they have found success in a variety of settings, including most recently language modeling and reasoning. To demystify…

Test-time augmentation -- the aggregation of predictions across transformed versions of a test input -- is a common practice in image classification. Traditionally, predictions are combined using a simple average. In this paper, we present…

We investigate distribution testing with access to non-adaptive conditional samples. In the conditional sampling model, the algorithm is given the following access to a distribution: it submits a query set $S$ to an oracle, which returns a…

The increased availability of massive data sets provides a unique opportunity to discover subtle patterns in their distributions, but also imposes overwhelming computational challenges. To fully utilize the information contained in big…

Test-time adaptation (TTA) enhances the zero-shot robustness under distribution shifts by leveraging unlabeled test data during inference. Despite notable advances, several challenges still limit its broader applicability. First, most…

Generative models have made significant impacts across various domains, largely due to their ability to scale during training by increasing data, computational resources, and model size, a phenomenon characterized by the scaling laws.…

Distribution shifts are ubiquitous in real-world machine learning applications, posing a challenge to the generalization of models trained on one data distribution to another. We focus on scenarios where data distributions vary across…

Currently, pre-trained language models (PLMs) do not cope well with the distribution shift problem, resulting in models trained on the training set failing in real test scenarios. To address this problem, the test-time adaptation (TTA)…

Inspired by the success of language models (LM), scaling up deep learning recommendation systems (DLRS) has become a recent trend in the community. All previous methods tend to scale up the model parameters during training time. However,…

Large language models (LLMs) have rapidly progressed into general-purpose agents capable of solving a broad spectrum of tasks. However, current models remain inefficient at reasoning: they apply fixed inference-time compute regardless of…

Test-time adaptation (TTA) adapts the pre-trained models to test distributions during the inference phase exclusively employing unlabeled test data streams, which holds great value for the deployment of models in real-world applications.…

In this paper, we propose energy-based sample adaptation at test time for domain generalization. Where previous works adapt their models to target domains, we adapt the unseen target samples to source-trained models. To this end, we design…

Their highly adaptive nature and the combinatorial explosion of possible configurations makes testing context-oriented programs hard. We propose a methodology to automate the generation of test scenarios for developers of feature-based…

Inference-time controllable generation is essential for real-world applications of unconditional diffusion models. However, most existing techniques focus on individual samples, struggling in applications that require the sample population…

In this paper, we have developed an approach to generate test data for path coverage based testing. The main challenge of this kind testing lies in its ability to build efficiently such a test suite in order to minimize the number of…

In zero-shot setting, test-time adaptation adjusts pre-trained models using unlabeled data from the test phase to enhance performance on unknown test distributions. Existing cache-enhanced TTA methods rely on a low-entropy criterion to…

Large-scale pre-trained language models have shown remarkable results in diverse NLP applications. Unfortunately, these performance gains have been accompanied by a significant increase in computation time and model size, stressing the need…

Test-time scaling has emerged as a promising direction for enhancing the reasoning capabilities of Large Language Models in last few years. In this work, we propose Population-Evolve, a training-free method inspired by Genetic Algorithms to…

We consider the problem of locating a jump discontinuity (change-point) in a smooth parametric regression model with a bounded covariate. It is assumed that one can sample the covariate at different values and measure the corresponding…