Related papers: Predictive Reasoning with Augmented Anomaly Contra…

Recent approaches in self-supervised learning of image representations can be categorized into different families of methods and, in particular, can be divided into contrastive and non-contrastive approaches. While differences between the…

In recent years, graph contrastive learning (GCL) has received increasing attention in recommender systems due to its effectiveness in reducing bias caused by data sparsity. However, most existing GCL models rely on heuristic approaches and…

Visual Commonsense Reasoning (VCR) remains a significant yet challenging research problem in the realm of visual reasoning. A VCR model generally aims at answering a textual question regarding an image, followed by the rationale prediction…

Self-supervised representation learning can mitigate the limitations in recognition tasks with few manually labeled data but abundant unlabeled data---a common scenario in sound event research. In this work, we explore unsupervised…

Machine learning (ML) has seen promising developments in materials science, yet its efficacy largely depends on detailed crystal structural data, which are often complex and hard to obtain, limiting their applicability in real-world…

In this paper, we investigate the research problem of unsupervised multi-view feature selection. Conventional solutions first simply combine multiple pre-constructed view-specific similarity structures into a collaborative similarity…

Visual reasoning models (VRMs) have recently shown strong cross-modal reasoning capabilities by integrating visual perception with language reasoning. However, they often suffer from overthinking, producing unnecessarily long reasoning…

Conversion rate (CVR) prediction plays an important role in advertising systems. Recently, supervised deep neural network-based models have shown promising performance in CVR prediction. However, they are data hungry and require an enormous…

Composed Image Retrieval (CIR) seeks to find a target image using a multi-modal query, which combines an image with modification text to pinpoint the target. While recent CIR methods have shown promise, they mainly focus on exploring…

Causal models provide rich descriptions of complex systems as sets of mechanisms by which each variable is influenced by its direct causes. They support reasoning about manipulating parts of the system and thus hold promise for addressing…

With the growing use of Retrieval-Augmented Generation (RAG), training large language models (LLMs) for context-sensitive reasoning and faithfulness is increasingly important. Existing RAG-oriented reinforcement learning (RL) methods rely…

Micro-video recommender systems suffer from the ubiquitous noises in users' behaviors, which might render the learned user representation indiscriminating, and lead to trivial recommendations (e.g., popular items) or even weird ones that…

Previous approaches to the task of implicit discourse relation recognition (IDRR) generally view it as a classification task. Even with pre-trained language models, like BERT and RoBERTa, IDRR still relies on complicated neural networks…

Visual reasoning with compositional natural language instructions, e.g., based on the newly-released Cornell Natural Language Visual Reasoning (NLVR) dataset, is a challenging task, where the model needs to have the ability to create an…

Large Language and Vision-Language Models (LLMs/VLMs) are increasingly used in safety-critical applications, yet their opaque decision-making complicates risk assessment and reliability. Uncertainty quantification (UQ) helps assess…

A pervasive challenge in Reinforcement Learning (RL) is the "curse of dimensionality" which is the exponential growth in the state-action space when optimizing a high-dimensional target task. The framework of curriculum learning trains the…

We propose Probabilistic Warp Consistency, a weakly-supervised learning objective for semantic matching. Our approach directly supervises the dense matching scores predicted by the network, encoded as a conditional probability distribution.…

Contrastive learning (CL) aims to learn useful representation without relying on expert annotations in the context of medical image segmentation. Existing approaches mainly contrast a single positive vector (i.e., an augmentation of the…

Abstract visual reasoning remains challenging as existing methods often prioritize either global context or local row-wise relations, failing to integrate both, and lack intermediate feature constraints, leading to incomplete rule capture…

Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced the reasoning capabilities of Large Language Models (LLMs) and is now being applied to Vision-Language Models (VLMs). However, vanilla RLVR for VLMs verifies…