Language model pretraining with next token prediction has proved effective for scaling
compute but is limited to the amount of available training data. Scaling reinforcement …

Dense process rewards have proven a more effective alternative to the sparse outcome-
level rewards in the inference-time scaling of large language models (LLMs), particularly in …

The rapid advancement of artificial intelligence, particularly with the development of Large
Language Models (LLMs) built on the transformer architecture, has redefined the …

We introduce MedXpertQA, a highly challenging and comprehensive benchmark to evaluate
expert-level medical knowledge and advanced reasoning. MedXpertQA includes 4,460 …

Supervised Fine-Tuning (SFT) is commonly used to train language models to imitate
annotated responses for given instructions. In this paper, we challenge this paradigm and …

Multi-sample aggregation strategies, such as majority voting and best-of-N sampling, are
widely used in contemporary large language models (LLMs) to enhance predictive accuracy …

Recent advances in text-based large language models (LLMs), particularly in the GPT series
and the o1 model, have demonstrated the effectiveness of scaling both training-time and …

Materials design is an important component of modern science and technology, yet
traditional approaches rely heavily on trial-and-error and can be inefficient. Computational …

Emerging large reasoning models (LRMs), such as DeepSeek-R1 models, leverage long
chain-of-thought (CoT) reasoning to generate structured intermediate steps, enhancing their …

Video generation has achieved significant advances through rectified flow techniques, but
issues like unsmooth motion and misalignment between videos and prompts persist. In this …