Related papers: TestNUC: Enhancing Test-Time Computing Approaches …

We address the problem of semi-supervised domain generalization (SSDG), where the distributions of train and test data differ, and only a small amount of labeled data along with a larger amount of unlabeled data are available during…

While pre-trained language model (PLM) fine-tuning has achieved strong performance in many NLP tasks, the fine-tuning stage can be still demanding in labeled data. Recent works have resorted to active fine-tuning to improve the label…

In class-incremental semantic segmentation, we have no access to the labeled data of previous tasks. Therefore, when incrementally learning new classes, deep neural networks suffer from catastrophic forgetting of previously learned…

Unsupervised image clustering methods often introduce alternative objectives to indirectly train the model and are subject to faulty predictions and overconfident results. To overcome these challenges, the current research proposes an…

Positive-Unlabeled (PU) learning aims to learn a model with rare positive samples and abundant unlabeled samples. Compared with classical binary classification, the task of PU learning is much more challenging due to the existence of many…

Aligning Large Language Models (LLMs) with human preferences through finetuning is resource-intensive, motivating lightweight alternatives at test time. We address test-time alignment through the lens of sequential decision making, a…

Large reasoning models (LRMs) have exhibited the capacity of enhancing reasoning performance via internal test-time scaling. Building upon this, a promising direction is to further scale test-time compute to unlock even greater reasoning…

Scaling test-time compute has emerged as a powerful mechanism for enhancing Large Language Model (LLM) performance. However, standard post-training paradigms, Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), optimize the…

Test-time scaling is a promising new approach to language modeling that uses extra test-time compute to improve performance. Recently, OpenAI's o1 model showed this capability but did not publicly share its methodology, leading to many…

Recent research has highlighted that Large Language Models (LLMs), even when trained to generate extended long reasoning steps, still face significant challenges on hard reasoning problems. However, much of the existing literature relies on…

Sequential test-time scaling is a promising training-free method to improve large reasoning model accuracy, but as currently implemented, significant limitations have been observed. Inducing models to think for longer can increase their…

We propose UnMixMatch, a semi-supervised learning framework which can learn effective representations from unconstrained unlabelled data in order to scale up performance. Most existing semi-supervised methods rely on the assumption that…

The reasoning capabilities of large language models (LLMs) have significantly advanced their performance by enabling in-depth understanding of diverse tasks. With growing interest in applying LLMs to the time series domain, this has proven…

As evaluation designs of large language models may shape our trajectory toward artificial general intelligence, comprehensive and forward-looking assessment is essential. Existing benchmarks primarily assess static knowledge, while…

Learning decent representations from unlabeled time-series data with temporal dynamics is a very challenging task. In this paper, we propose an unsupervised Time-Series representation learning framework via Temporal and Contextual…

Deploying models on target domain data subject to distribution shift requires adaptation. Test-time training (TTT) emerges as a solution to this adaptation under a realistic scenario where access to full source domain data is not available…

Best-of-N selection is a key technique for improving the reasoning performance of Large Language Models (LLMs) through increased test-time computation. Current state-of-the-art methods often employ computationally intensive reward models…

Large Language Models (LLMs) have the impressive ability to perform in-context learning (ICL) from only a few examples, but the success of ICL varies widely from task to task. Thus, it is important to quickly determine whether ICL is…

Pre-trained code models have recently achieved substantial improvements in many code intelligence tasks. These models are first pre-trained on large-scale unlabeled datasets in a task-agnostic manner using self-supervised learning, and then…

Unsupervised domain adaptation methods aim to generalize well on unlabeled test data that may have a different (shifted) distribution from the training data. Such methods are typically developed on image data, and their application to time…