相关论文: Self-Supervised Representation Learning as Mutual …

We study the relative effects of data augmentations, pretraining algorithms, and model architectures in Self-Supervised Learning (SSL). While the recent literature in this space leaves the impression that the pretraining algorithm is of…

Generally speaking, the goal of constructive learning could be seen as, given an example set of structured objects, to generate novel objects with similar properties. From a statistical-relational learning (SRL) viewpoint, the task can be…

While Multimodal Large Language Models (MLLMs) excel at vision-language tasks, the cost of their language-driven training on internal visual foundational competence remains unclear. In this paper, we conduct a detailed diagnostic analysis…

We introduce SIRI, Scaling Iterative Reinforcement Learning with Interleaved Compression, a simple yet effective RL approach for Large Reasoning Models (LRMs) that enables more efficient and accurate reasoning. Existing studies have…

Incorporating heterogeneous representations from different architectures has facilitated various vision tasks, e.g., some hybrid networks combine transformers and convolutions. However, complementarity between such heterogeneous…

Pre-trained Language Model (PLM) is nowadays the mainstay of Unsupervised Sentence Representation Learning (USRL). However, PLMs are sensitive to the frequency information of words from their pre-training corpora, resulting in anisotropic…

Representation learning has been widely studied in the context of meta-learning, enabling rapid learning of new tasks through shared representations. Recent works such as MAML have explored using fine-tuning-based metrics, which measure the…

Self-supervised representation learning (SSRL) has demonstrated superior performance than supervised models for tasks including phoneme recognition. Training SSRL models poses a challenge for low-resource languages where sufficient…

Tackling pattern recognition problems in areas such as computer vision, bioinformatics, speech or text recognition is often done best by taking into account task-specific statistical relations between output variables. In structured…

Self-supervised learning (SSL) as an effective paradigm of representation learning has achieved tremendous success on various curated datasets in diverse scenarios. Nevertheless, when facing the long-tailed distribution in real-world…

Self-supervised Learning (SSL) including the mainstream contrastive learning has achieved great success in learning visual representations without data annotations. However, most of methods mainly focus on the instance level information…

Disentangled representation has been widely explored in many fields due to its maximal compactness, interpretability and versatility. Recommendation system also needs disentanglement to make representation more explainable and general for…

Optimization modeling is fundamental to decision-making across diverse domains. Despite progress in automating optimization formulation from natural language descriptions, Large Language Models (LLMs) often struggle to generate formally…

This work proposes a new way of combining independently trained classifiers over space and time. Combination over space means that the outputs of spatially distributed classifiers are aggregated. Combination over time means that the…

While neural sequence learning methods have made significant progress in single-document summarization (SDS), they produce unsatisfactory results on multi-document summarization (MDS). We observe two major challenges when adapting SDS…

In recent years, self-supervised learning (SSL) frameworks have been extensively applied to sensor-based Human Activity Recognition (HAR) in order to learn deep representations without data annotations. While SSL frameworks reach…

Self-supervised learning (SSL) has emerged as a powerful technique for learning visual representations. While recent SSL approaches achieve strong results in global image understanding, they are limited in capturing the structured…

The landscape of self-supervised learning (SSL) is currently dominated by generative approaches (e.g., MAE) that reconstruct raw low-level data, and predictive approaches (e.g., I-JEPA) that predict high-level abstract embeddings. While…

Multi-objective reinforcement learning (MORL) algorithms tackle sequential decision problems where agents may have different preferences over (possibly conflicting) reward functions. Such algorithms often learn a set of policies (each…

With the rapid growth of data, it is becoming increasingly difficult to train or improve deep learning models with the right subset of data. We show that this problem can be effectively solved at an additional labeling cost by targeted data…