Related papers: Tree-Based Reconstructive Partitioning: A Novel Lo…

The advancement of Large Language Model (LLM)-powered agents has enabled automated task processing through reasoning and tool invocation capabilities. However, existing frameworks often operate under the idealized assumption that tool…

Text-to-level generation aims to translate natural language descriptions into structured game levels, enabling intuitive control over procedural content generation. While prior text-to-level generators are typically limited to a single game…

Multimodal misinformation poses an escalating challenge that often evades traditional detectors, which are opaque black boxes and fragile against new manipulation tactics. We present Probabilistic Concept Graph Reasoning (PCGR), an…

Neural table-to-text generation approaches are data-hungry, limiting their adaptation for low-resource real-world applications. Previous works mostly resort to Pre-trained Language Models (PLMs) to generate fluent summaries of a table.…

The emergence of large language models (LLMs) has revolutionized the capabilities of text comprehension and generation. Multi-modal generation attracts great attention from both the industry and academia, but there is little work on…

Generative Adversarial Networks (GANs) are a machine learning approach capable of generating novel example outputs across a space of provided training examples. Procedural Content Generation (PCG) of levels for video games could benefit…

Constraint-based game content generators that learn local constraints from existing content, such as Wave Function Collapse (WFC), can generate visually satisfying game levels but face challenges in guaranteeing global properties, such as…

Procedural terrain generation for video games has been traditionally been done with smartly designed but handcrafted algorithms that generate heightmaps. We propose a first step toward the learning and synthesis of these using recent…

Textual data question answering has gained significant attention due to its growing applicability. Recently, a novel approach leveraging the Retrieval-Augmented Generation (RAG) method was introduced, utilizing the Prize-Collecting Steiner…

The use of machine learning algorithms in finance, medicine, and criminal justice can deeply impact human lives. As a consequence, research into interpretable machine learning has rapidly grown in an attempt to better control and fix…

Agentic code generation requires large language models (LLMs) capable of complex context management and multi-step reasoning. Prior multi-agent frameworks attempt to address these challenges through collaboration, yet they often suffer from…

Machine learning (ML) has seen promising developments in materials science, yet its efficacy largely depends on detailed crystal structural data, which are often complex and hard to obtain, limiting their applicability in real-world…

Text embedding and generative tasks are usually trained separately based on large language models (LLMs) nowadays. This causes a large amount of training cost and deployment effort. Context compression is also a challenging and pressing…

Advancements in model algorithms, the growth of foundational models, and access to high-quality datasets have propelled the evolution of Artificial Intelligence Generated Content (AIGC). Despite its notable successes, AIGC still faces…

We introduce the Chronicle Challenge as an optional addition to the Settlement Generation Challenge in Minecraft. One of the foci of the overall competition is adaptive procedural content generation (PCG), an arguably under-explored problem…

We propose a method to construct the initial tensor representation of partition functions and observables for the tensor renormalization group (TRG). The TRG is a numerical calculation technique that utilizes a tensor network…

Fine-tuned pre-trained language models (PLMs) have achieved awesome performance on almost all NLP tasks. By using additional prompts to fine-tune PLMs, we can further stimulate the rich knowledge distributed in PLMs to better serve…

Recent years have seen a number of proposals for performing Natural Language Generation (NLG) based in large part on statistical techniques. Despite having many attractive features, we argue that these existing approaches nonetheless have…

Retrieval-augmented generation (RAG) is a popular technique for using large language models (LLMs) to build customer-support, question-answering solutions. In this paper, we share our team's practical experience building and maintaining…

Process reward models (PRMs) enhance complex reasoning in large language models (LLMs) by evaluating candidate solutions step-by-step and selecting answers based on aggregated step scores. While effective in domains such as mathematics,…