相关论文: Systematic Generalization on gSCAN: What is Nearly…

Systematic Generalization refers to a learning algorithm's ability to extrapolate learned behavior to unseen situations that are distinct but semantically similar to its training data. As shown in recent work, state-of-the-art deep learning…

Contrarily to humans who have the ability to recombine familiar expressions to create novel ones, modern neural networks struggle to do so. This has been emphasized recently with the introduction of the benchmark dataset "gSCAN" (Ruis et…

Humans easily interpret expressions that describe unfamiliar situations composed from familiar parts ("greet the pink brontosaurus by the ferris wheel"). Modern neural networks, by contrast, struggle to interpret novel compositions. In this…

Compositional generalization, the ability of intelligent models to extrapolate understanding of components to novel compositions, is a fundamental yet challenging facet in AI research, especially within multimodal environments. In this…

Humans are remarkably flexible when understanding new sentences that include combinations of concepts they have never encountered before. Recent work has shown that while deep networks can mimic some human language abilities when presented…

Vision models trained on multimodal datasets can benefit from the wide availability of large image-caption datasets. A recent model (CLIP) was found to generalize well in zero-shot and transfer learning settings. This could imply that…

One of the primary challenges faced by deep learning is the degree to which current methods exploit superficial statistics and dataset bias, rather than learning to generalise over the specific representations they have experienced. This is…

Grounding natural language queries in graphical user interfaces (GUIs) presents a challenging task that requires models to comprehend diverse UI elements across various applications and systems, while also accurately predicting the spatial…

Despite their practical success, modern seq2seq architectures are unable to generalize systematically on several SCAN tasks. Hence, it is not clear if SCAN-style compositional generalization is useful in realistic NLP tasks. In this work,…

Humans can reason compositionally whilst grounding language utterances to the real world. Recent benchmarks like ReaSCAN use navigation tasks grounded in a grid world to assess whether neural models exhibit similar capabilities. In this…

Semantic segmentation in a supervised learning manner has achieved significant progress in recent years. However, its performance usually drops dramatically due to the data-distribution discrepancy between seen and unseen domains when we…

The goal of compositional generalization benchmarks is to evaluate how well models generalize to new complex linguistic expressions. Existing benchmarks often focus on lexical generalization, the interpretation of novel lexical items in…

The ability to compositionally map language to referents, relations, and actions is an essential component of language understanding. The recent gSCAN dataset (Ruis et al. 2020, NeurIPS) is an inspiring attempt to assess the capacity of…

As machine learning becomes increasingly central to molecular design, it is vital to ensure the reliability of learnable protein-ligand scoring functions on novel protein targets. While many scoring functions perform well on standard…

Spatial grounding, the process of associating natural language expressions with corresponding image regions, has rapidly advanced due to the introduction of transformer-based models, significantly enhancing multimodal representation and…

Compositional generalization is a troubling blind spot for neural language models. Recent efforts have presented techniques for improving a model's ability to encode novel combinations of known inputs, but less work has focused on…

Multi-modal learning has achieved remarkable success by integrating information from various modalities, achieving superior performance in tasks like recognition and retrieval compared to uni-modal approaches. However, real-world scenarios…

To build general-purpose artificial intelligence systems that can deal with unknown variables across unknown domains, we need benchmarks that measure how well these systems perform on tasks they have never seen before. A prerequisite for…

Recent advancements in 3D reconstruction methods and vision-language models have propelled the development of multi-modal 3D scene understanding, which has vital applications in robotics, autonomous driving, and virtual/augmented reality.…

Systematic compositionality is an essential mechanism in human language, allowing the recombination of known parts to create novel expressions. However, existing neural models have been shown to lack this basic ability in learning symbolic…