Related papers: Game Level Blending using a Learned Level Represen…

Recently, several approaches have emerged for generating neural representations with multiple levels of detail (LODs). LODs can improve the rendering by using lower resolutions and smaller model sizes when appropriate. However, existing…

In games, as in and many other domains, design validation and testing is a huge challenge as systems are growing in size and manual testing is becoming infeasible. This paper proposes a new approach to automated game validation and testing.…

Modern DNN-based recommendation systems rely on training-derived embeddings of sparse features. Input sparsity makes obtaining high-quality embeddings for rarely-occurring categories harder as their representations are updated infrequently.…

Obtaining a single-vector representation from a Large Language Model's (LLM) token-level outputs is a critical step for nearly all sentence-level tasks. However, standard pooling methods like mean or max aggregation treat tokens as an…

Most recent few-shot learning (FSL) methods are based on meta-learning with episodic training. In each meta-training episode, a discriminative feature embedding and/or classifier are first constructed from a support set in an inner loop,…

Node representations, or embeddings, are low-dimensional vectors that capture node properties, typically learned through unsupervised structural similarity objectives or supervised tasks. While recent efforts have focused on explaining…

Ideal or real - that is the question.In this work, we explore whether principles from game theory can be effectively applied to the evaluation of large language models (LLMs). This inquiry is motivated by the growing inadequacy of…

Code-mixing, the practice of alternating between two or more languages in an utterance, is a common phenomenon in multilingual communities. Due to the colloquial nature of code-mixing, there is no singular correct way to translate an…

In this paper, we present an approach for fault-tolerant synthesis by combining predefined patterns for fault-tolerance with algorithmic game solving. A non-fault-tolerant system, together with the relevant fault hypothesis and…

Play style identification can provide valuable game design insights and enable adaptive experiences, with the potential to improve game playing agents. Previous work relies on domain knowledge to construct play trace representations using…

The metadata about scientific experiments published in online repositories have been shown to suffer from a high degree of representational heterogeneity---there are often many ways to represent the same type of information, such as a…

Foundation models must handle multiple generative processes, yet mechanistic interpretability largely studies capabilities in isolation; it remains unclear how a single transformer organizes multiple, potentially conflicting "world models".…

Graph representation learning is a fast-growing field where one of the main objectives is to generate meaningful representations of graphs in lower-dimensional spaces. The learned embeddings have been successfully applied to perform various…

Procedural Content Generation via Reinforcement Learning (PCGRL) offers a method for training controllable level designer agents without the need for human datasets, using metrics that serve as proxies for level quality as rewards. Existing…

Reasoning is essential for the development of large knowledge graphs, especially for completion, which aims to infer new triples based on existing ones. Both rules and embeddings can be used for knowledge graph reasoning and they have their…

In this work, we consider the problem of procedural content generation for video game levels. Prior approaches have relied on evolutionary search (ES) methods capable of generating diverse levels, but this generation procedure is slow,…

Catastrophic forgetting during knowledge injection impairs the ability of large language models to acquire new knowledge without overwriting previously mastered knowledge. Recent studies analyze forgetting from a gradient similarity…

Many machine learning systems today are trained on large amounts of human-annotated data. Data annotation tasks that require a high level of competency make data acquisition expensive, while the resulting labels are often subjective,…

Embedding learning of categorical features (e.g. user/item IDs) is at the core of various recommendation models including matrix factorization and neural collaborative filtering. The standard approach creates an embedding table where each…

Representation learning is a critical ingredient for natural language processing systems. Recent Transformer language models like BERT learn powerful textual representations, but these models are targeted towards token- and sentence-level…