The generation of plausible crystal structures is often the first step in predicting the structure
and properties of a material from its chemical composition. However, most current methods …

Existing large language model-based code generation pipelines typically use beam search
or sampling algorithms during the decoding process. Although the programs they generate …

Symbolic regression (SR) is a challenging task in machine learning that involves finding a
mathematical expression for a function based on its values. Recent advancements in SR …

We propose controlled decoding (CD), a novel off-policy reinforcement learning method to
control the autoregressive generation from language models towards high reward …

Recent works like Tree-of-Thought (ToT) and Reasoning via Planning (RAP) aim to augment
the multi-step reasoning capabilities of LLMs by using tree-search algorithms. These …

Watermarking is a technical means to dissuade malfeasant usage of Large Language
Models. This paper proposes a novel watermarking scheme, so-called WaterMax, that …

Inference-time search algorithms such as Monte-Carlo Tree Search (MCTS) may seem
unnecessary when generating natural language text based on state-of-the-art reinforcement …

Aligning large language models with human objectives is paramount, yet common
approaches including RLHF suffer from unstable and resource-intensive training. In …

Creating high-quality scientific figures can be time-consuming and challenging, even though
sketching ideas on paper is relatively easy. Furthermore, recreating existing figures that are …

Enhancing the reasoning capabilities of large language models (LLMs) remains a key
challenge, especially for tasks that require complex, multi-step decision-making. Humans …