Related papers: CrystalReasoner: Reasoning and RL for Property-Con…

Crystal-structure phase mapping is a core, long-standing challenge in materials science that requires identifying crystal structures, or mixtures thereof, in synthesized materials. Materials science experts excel at solving simple systems…

Reasoning LLMs (RLMs) such as OpenAI o1, DeepSeek-R1, and Qwen3 deliver strong multi-step reasoning through chain-of-thought generation, but their large model sizes and lengthy decode-time outputs make them costly to deploy and unsuitable…

While Large Language Models (LLMs) demonstrate exceptional performance in surface-level text generation, their nature in handling complex multi-step reasoning tasks often remains one of ``statistical fitting'' rather than systematic logical…

Generating high-quality stories spanning thousands of tokens requires competency across a variety of skills, from tracking plot and character arcs to keeping a consistent and engaging style. Due to the difficulty of sourcing labeled…

Large language models can exhibit emergent reasoning behaviors, often manifested as recurring lexical patterns (e.g., "wait," indicating verification). However, complex reasoning trajectories remain sparse in unconstrained sampling, and…

Self-supervised neural language models have recently achieved unprecedented success, from natural language processing to learning the languages of biological sequences and organic molecules. These models have demonstrated superior…

Conditional layout generation aims to automatically generate visually appealing and semantically coherent layouts from user-defined constraints. While recent methods based on generative models have shown promising results, they typically…

Large language models (LLMs) tackle complex tasks by generating long chains of thought or "reasoning traces" that act as latent variables in the generation of an output given a query. A model's ability to generate such traces can be…

Large Language Models (LLMs) are increasingly deployed in critical applications requiring reliable reasoning, yet their internal reasoning processes remain difficult to evaluate systematically. Existing methods focus on final-answer…

Generative models trained at scale can now produce text, video, and more recently, scientific data such as crystal structures. In applications of generative approaches to materials science, and in particular to crystal structures, the…

Retrieval-augmented generation (RAG) improves knowledge-intensive question answering by incorporating external evidence. However, existing RAG methods still suffer from hallucinations and subtle reasoning errors. Recent studies introduce…

The powerful generative capacity of Large Language Models (LLMs) has instigated a paradigm shift in recommendation. However, existing generative models (e.g., OneRec) operate as implicit predictors, critically lacking the capacity for…

Human beings solve complex problems through critical thinking, where reasoning and evaluation are intertwined to converge toward correct solutions. However, most existing large language models (LLMs) treat the reasoning and verification as…

Recent advancements in large language models (LLMs) underscore the need for stronger reasoning capabilities to solve complex problems effectively. While Chain-of-Thought (CoT) reasoning has been a step forward, it remains insufficient for…

Process Reward Models (PRMs) aim to improve multi-step reasoning in Large Language Models (LLMs) by supervising intermediate steps and identifying errors. However, building effective PRMs remains challenging due to the lack of scalable,…

Artificial intelligence (AI) is transforming materials science, enabling both theoretical advancements and accelerated materials discovery. Recent progress in crystal generation models, which design crystal structures for targeted…

Machine Learning models have emerged as a powerful tool for fast and accurate prediction of different crystalline properties. Exiting state-of-the-art models rely on a single modality of crystal data i.e. crystal graph structure, where they…

Recent advances in reasoning-enhanced large language models (LLMs) and multimodal LLMs (MLLMs) have significantly improved performance in complex tasks, yet medical AI models often overlook the structured reasoning processes inherent in…

Drawing inspiration from the achievements of natural language processing, we adopt self-supervised learning and utilize an equivariant graph neural network to develop a unified platform designed for training generative models capable of…

This work characterizes large language models' chain-of-thought generation as a structured trajectory through representation space. We show that mathematical reasoning traverses functionally ordered, step-specific subspaces that become…