Related papers: What If Consensus Lies? Selective-Complementary Re…

Test-time reinforcement learning (TTRL) enables large language models (LLMs) to self-improve on unlabeled inputs, but its effectiveness critically depends on how reward signals are estimated without ground-truth supervision. Most existing…

This paper presents a novel self-supervised learning method for handling conversational documents consisting of transcribed text of human-to-human conversations. One of the key technologies for understanding conversational documents is…

Recently, Semi-Supervised Learning (SSL) has shown much promise in leveraging unlabeled data while being provided with very few labels. In this paper, we show that ignoring the labels altogether for whole epochs intermittently during…

The past few years have witnessed a remarkable advance in deep learning for EEG-based sleep stage classification (SSC). However, the success of these models is attributed to possessing a massive amount of labeled data for training, limiting…

Reinforcement learning (RL) solves sequential decision-making problems via a trial-and-error process interacting with the environment. While RL achieves outstanding success in playing complex video games that allow huge trial-and-error,…

Given an unlabeled dataset and an annotation budget, we study how to selectively label a fixed number of instances so that semi-supervised learning (SSL) on such a partially labeled dataset is most effective. We focus on selecting the right…

In sequential decision-making problems, Return-Conditioned Supervised Learning (RCSL) has gained increasing recognition for its simplicity and stability in modern decision-making tasks. Unlike traditional offline reinforcement learning (RL)…

Localizing keypoints of an object is a basic visual problem. However, supervised learning of a keypoint localization network often requires a large amount of data, which is expensive and time-consuming to obtain. To remedy this, there is an…

Sentence Representation Learning (SRL) is a fundamental task in Natural Language Processing (NLP), with the Contrastive Learning of Sentence Embeddings (CSE) being the mainstream technique due to its superior performance. An intriguing…

Structured texts refer to texts containing structured elements beyond plain texts, such as code snippets and placeholders. Such structured texts increasingly require segmentation into semantically meaningful components, which cannot be…

Learning to rank (LTR) plays a crucial role in various Information Retrieval (IR) tasks. Although supervised LTR methods based on fine-grained relevance labels (e.g., document-level annotations) have achieved significant success, their…

We introduce a control-tutored reinforcement learning (CTRL) algorithm. The idea is to enhance tabular learning algorithms by means of a control strategy with limited knowledge of the system model. By tutoring the learning process, the…

The rising cost of acquiring supervised data has driven significant interest in self-improvement for large language models (LLMs). Straightforward unsupervised signals like majority voting have proven effective in generating pseudo-labels…

Semi-supervised learning (SSL) tackles the label missing problem by enabling the effective usage of unlabeled data. While existing SSL methods focus on the traditional setting, a practical and challenging scenario called label Missing Not…

Most reinforcement learning (RL) methods for training large language models (LLMs) require ground-truth labels or task-specific verifiers, limiting scalability when correctness is ambiguous or expensive to obtain. We introduce Reinforcement…

Despite significant advances in Large Reasoning Models (LRMs) driven by reinforcement learning with verifiable rewards (RLVR), this paradigm is fundamentally limited in specialized or novel domains where such supervision is prohibitively…

Class-agnostic motion prediction methods aim to comprehend motion within open-world scenarios, holding significance for autonomous driving systems. However, training a high-performance model in a fully-supervised manner always requires…

Federated learning (FL) is a promising way to use the computing power of mobile devices while maintaining the privacy of users. Current work in FL, however, makes the unrealistic assumption that the users have ground-truth labels on their…

Large Language Models (LLMs) are powerful tools with profound societal impacts, yet their ability to generate responses to diverse and uncontrolled inputs leaves them vulnerable to adversarial attacks. While existing defenses often struggle…

Test-time scaling (TTS) improves large language models (LLMs) by allocating additional compute at inference time. In practice, TTS is often achieved through parallel scaling: generating multiple candidate responses and selecting the best…