相关论文: Hallucinating Beyond Observation: Learning to Comp…

Vision-language models (VLMs) have recently shown remarkable capabilities in visual understanding and generation, but remain vulnerable to adversarial manipulations of visual content. Prior object-hiding attacks primarily rely on…

Network embedding is an effective technique to learn the low-dimensional representations of nodes in networks. Real-world networks are usually with multiplex or having multi-view representations from different relations. Recently, there has…

We deal with the problem of information fusion driven satellite image/scene classification and propose a generic hallucination architecture considering that all the available sensor information are present during training while some of the…

Real-time scene comprehension is a key advance in artificial intelligence, enhancing robotics, surveillance, and assistive tools. However, hallucination remains a challenge. AI systems often misinterpret visual inputs, detecting nonexistent…

Unsupervised point cloud completion aims at estimating the corresponding complete point cloud of a partial point cloud in an unpaired manner. It is a crucial but challenging problem since there is no paired partial-complete supervision that…

Day-to-night unpaired image translation is important to downstream tasks but remains challenging due to large appearance shifts and the lack of direct pixel-level supervision. Existing methods often introduce semantic hallucinations, where…

Learning based methods have shown very promising results for the task of depth estimation in single images. However, most existing approaches treat depth prediction as a supervised regression problem and as a result, require vast quantities…

Whole slide image (WSI) normalization remains a vital preprocessing step in computational pathology. Increasingly driven by deep learning, these models learn to approximate data distributions from training examples. This often results in…

When navigating in urban environments, many of the objects that need to be tracked and avoided are heavily occluded. Planning and tracking using these partial scans can be challenging. The aim of this work is to learn to complete these…

Depth perception models are typically trained on non-interactive datasets with predefined camera trajectories. However, this often introduces systematic biases into the learning process correlated to specific camera paths chosen during data…

The field of visual representation learning has seen explosive growth in the past years, but its benefits in robotics have been surprisingly limited so far. Prior work uses generic visual representations as a basis to learn (task-specific)…

Multi-modal Large Language Models (MLLMs) tuned on machine-generated instruction-following data have demonstrated remarkable performance in various multi-modal understanding and generation tasks. However, the hallucinations inherent in…

Image-based 3D detection is an indispensable component of the perception system for autonomous driving. However, it still suffers from the unsatisfying performance, one of the main reasons for which is the limited training data.…

Contextual hallucinations -- statements unsupported by given context -- remain a significant challenge in AI. We demonstrate a practical interpretability insight: a generator-agnostic observer model detects hallucinations via a single…

Few-shot language learners adapt knowledge from a pre-trained model to recognize novel classes from a few-labeled sentences. In such settings, fine-tuning a pre-trained language model can cause severe over-fitting. In this paper, we propose…

Abstractive summarization systems today produce fluent and relevant output, but often "hallucinate" statements not supported by the source text. We analyze the connection between hallucinations and training data, and find evidence that…

Multimodal language models can exhibit hallucinations in their outputs, which limits their reliability. The ability to automatically detect these errors is important for mitigating them, but has been less explored and existing efforts do…

Learning visuomotor control policies in robotic systems is a fundamental problem when aiming for long-term behavioral autonomy. Recent supervised-learning-based vision and motion perception systems, however, are often separately built with…

Large-scale pre-training has shown promising results on the vision-and-language navigation (VLN) task. However, most existing pre-training methods employ discrete panoramas to learn visual-textual associations. This requires the model to…

Recent attempts for unsupervised landmark learning leverage synthesized image pairs that are similar in appearance but different in poses. These methods learn landmarks by encouraging the consistency between the original images and the…