相关论文: On (Emergent) Systematic Generalisation and Compos…

With the rapid development of deep learning, most of current state-of-the-art techniques in natural langauge processing are based on deep learning models trained with argescaled static textual corpora. However, we human beings learn and…

Causal modeling has long been an attractive topic for many researchers and in recent decades there has seen a surge in theoretical development and discovery algorithms. Generally discovery algorithms can be divided into two approaches:…

In text-to-SQL tasks -- as in much of NLP -- compositional generalization is a major challenge: neural networks struggle with compositional generalization where training and test distributions differ. However, most recent attempts to…

Diffusion models excel at short-horizon robot planning, yet scaling them to long-horizon tasks remains challenging due to computational constraints and limited training data. Existing compositional approaches stitch together short segments…

Flexible neural sequence models outperform grammar- and automaton-based counterparts on a variety of tasks. However, neural models perform poorly in settings requiring compositional generalization beyond the training data -- particularly to…

Model robustness against adversarial examples of single perturbation type such as the $\ell_{p}$-norm has been widely studied, yet its generalization to more realistic scenarios involving multiple semantic perturbations and their…

Visual concepts (e.g., red apple, big elephant) are often semantically compositional and each element of the compositions can be reused to construct novel concepts (e.g., red elephant). Compositional feature synthesis, which generates image…

Generalization is often regarded as an essential property of machine learning systems. However, perhaps not every component of a system needs to generalize. Training models for generalization typically produces entangled representations at…

Compositional zero-shot learning (CZSL) refers to recognizing unseen compositions of known visual primitives, which is an essential ability for artificial intelligence systems to learn and understand the world. While considerable progress…

Large pre-trained time series foundation models (TSFMs) have demonstrated promising zero-shot performance across a wide range of domains. However, a question remains: Do TSFMs succeed by memorizing patterns in training data, or do they…

Automatic short answer scoring (ASAS) helps reduce the grading burden on educators but often lacks detailed, explainable feedback. Existing methods in ASAS with feedback (ASAS-F) rely on fine-tuning language models with limited datasets,…

Language-enabled robots have been widely studied over the past years to enable natural human-robot interaction and teaming in various real-world applications. Language-enabled robots must be able to comprehend referring expressions to…

Thinking aloud is an effective meta-cognitive strategy human reasoners apply to solve difficult problems. We suggest to improve the reasoning ability of pre-trained neural language models in a similar way, namely by expanding a task's…

The performance of generative zero-shot methods mainly depends on the quality of generated features and how well the model facilitates knowledge transfer between visual and semantic domains. The quality of generated features is a direct…

Compositional generalization refers to a model's capability to generalize to newly composed input data based on the data components observed during training. It has triggered a series of compositional generalization analysis on different…

Compositional generalization is a basic and essential intellective capability of human beings, which allows us to recombine known parts readily. However, existing neural network based models have been proven to be extremely deficient in…

In this paper, we investigate whether artificial agents can develop a shared language in an ecological setting where communication relies on a sensory-motor channel. To this end, we introduce the Graphical Referential Game (GREG) where a…

We equip a smaller Language Model to generalise to answering challenging compositional questions that have not been seen in training. To do so we propose a combination of multitask supervised pretraining on up to 93 tasks designed to…

The soft-thinking paradigm for Large Language Model (LLM) reasoning can outperform the conventional discrete-token Chain-of-Thought (CoT) reasoning in some scenarios, underscoring its research and application value. However, while the…

Despite a multitude of empirical studies, little consensus exists on whether neural networks are able to generalise compositionally, a controversy that, in part, stems from a lack of agreement about what it means for a neural model to be…