Related papers: Navigating Ideation Space: Decomposed Conceptual R…

Semantic communication has recently attracted significant interest from both industry and academia due to its potential to transform the existing data-focused communication architecture towards a more generally intelligent and goal-oriented…

With the growing popularity of general-purpose Large Language Models (LLMs), comes a need for more global explanations of model behaviors. Concept-based explanations arise as a promising avenue for explaining high-level patterns learned by…

Inference scaling methods for LLMs often rely on decomposing problems into steps (or groups of tokens), followed by sampling and selecting the best next steps. However, these steps and their sizes are often predetermined or manually…

Scientific retrieval is essential for advancing scientific knowledge discovery. Within this process, document reranking plays a critical role in refining first-stage retrieval results. However, standard LLM listwise reranking faces…

The advances in deep learning have enabled machine learning methods to outperform human beings in various areas, but it remains a great challenge for a well-trained model to quickly adapt to a new task. One promising solution to realize…

The ability to interpret and intervene model decisions is important for the adoption of computer-aided diagnosis methods in clinical workflows. Recent concept-based methods link the model predictions with interpretable concepts and modify…

Evaluating AI-generated research ideas typically relies on LLM judges or human panels -- both subjective and disconnected from actual research impact. We introduce HindSight, a time-split evaluation framework that measures idea quality by…

With the recent success of pre-trained models in NLP, a significant focus was put on interpreting their representations. One of the most prominent approaches is structural probing (Hewitt and Manning, 2019), where a linear projection of…

State-of-the-art natural language processing models have been shown to achieve remarkable performance in 'closed-world' settings where all the labels in the evaluation set are known at training time. However, in real-world settings, 'novel'…

The availability of large idea repositories (e.g., the U.S. patent database) could significantly accelerate innovation and discovery by providing people with inspiration from solutions to analogous problems. However, finding useful…

A word may contain one or more hidden concepts. While the "animal" word evokes many images in our minds and encapsulates many concepts (birds, dogs, cats, crocodiles, etc.), the `parrot' word evokes a single image (a colored bird with a…

Innovation, typically spurred by reusing, recombining, and synthesizing existing concepts, is expected to result in an exponential growth of the concept space over time. However, our statistical analysis of TechNet, which is a comprehensive…

Capturing the composition patterns of relations is a vital task in knowledge graph completion. It also serves as a fundamental step towards multi-hop reasoning over learned knowledge. Previously, several rotation-based translational methods…

A key challenge in lifelong imitation learning (LIL) is enabling agents to acquire new skills from expert demonstrations while retaining prior knowledge. This requires preserving the low-dimensional manifolds and geometric structures that…

We are born with the ability to learn concepts by comparing diverse observations. This helps us to understand the new world in a compositional manner and facilitates extrapolation, as objects naturally consist of multiple concepts. In this…

Language models (LMs) can perform complex reasoning either end-to-end, with hidden latent state, or compositionally, with transparent intermediate state. Composition offers benefits for interpretability and safety, but may need workflow…

We conjecture that creativity and the perception of creativity are, at least to some extent, shaped by embodiment. This makes embodiment highly relevant for Computational Creativity (CC) research, but existing research is scarce and the use…

The scientific literature is a large information network linking various actors (laboratories, companies, institutions, etc.). The vast amount of data generated by this network constitutes a dynamic heterogeneous attributed network (HAN),…

Knowledge Distillation (KD) is one proposed solution to large model sizes and slow inference speed in semantic segmentation. In our research we identify 25 proposed distillation loss terms from 14 publications in the last 4 years.…

We present a system for bottom-up cumulative learning of myriad concepts corresponding to meaningful character strings, and their part-related and prediction edges. The learning is self-supervised in that the concepts discovered are used as…