Related papers: Scaling Behavior Cloning Improves Causal Reasoning…

The human ability to learn rules and solve problems has been a central concern of cognitive science research since the field's earliest days. But we do not just follow rules and solve problems given to us by others: we modify those rules,…

Neural network-based emulators for the inference of stellar parameters and elemental abundances represent an increasingly popular methodology in modern spectroscopic surveys. However, these approaches are often constrained by their…

This paper examines the reasoning capabilities of Large Language Models (LLMs) from a novel perspective, focusing on their ability to operate within formally specified, rule-governed environments. We evaluate four LLMs (Gemini 2.5 Pro and…

Training generalist policies for robotic manipulation has shown great promise, as they enable language-conditioned, multi-task behaviors across diverse scenarios. However, evaluating these policies remains difficult because real-world…

The application of role-playing large language models (LLMs) is rapidly expanding in both academic and commercial domains, driving an increasing demand for high-precision role-playing models. Simultaneously, the rapid advancement of…

While large-scale sequence modeling from offline data has led to impressive performance gains in natural language and image generation, directly translating such ideas to robotics has been challenging. One critical reason for this is that…

Achieving optimal performance of video diffusion transformers within given data and compute budget is crucial due to their high training costs. This necessitates precisely determining the optimal model size and training hyperparameters…

In recent years, foundational models have revolutionized the fields of language and vision, demonstrating remarkable abilities in understanding and generating complex data; however, similar advances in user behavior modeling have been…

The scaling law is becoming a fundamental law in many machine learning areas. That is, test error falls off with the power law when increasing training data, model size, and computing resource. However, whether this law is suitable for the…

Imitation learning methods seek to learn from an expert either through behavioral cloning (BC) of the policy or inverse reinforcement learning (IRL) of the reward. Such methods enable agents to learn complex tasks from humans that are…

Generative recommendation models can model user behavior as sequences of events and provide a shared backbone for multiple recommendation tasks. In production, however, pre-training gains do not automatically translate into downstream…

Recent work has advocated for training AI models on ever-larger datasets, arguing that as the size of a dataset increases, the performance of a model trained on that dataset will correspondingly increase (referred to as "scaling laws"). In…

A human-like chess engine should mimic the style, errors, and consistency of a strong human player rather than maximize playing strength. We show that training from move sequences alone forces a model to learn two capabilities: state…

Recent works have shown that machine learning models improve at a predictable rate with the total amount of training data, leading to scaling laws that describe the relationship between error and dataset size. These scaling laws can help…

Test-time scaling improves the reasoning capabilities of large language models (LLMs) by allocating extra compute to generate longer Chains-of-Thoughts (CoTs). This enables models to tackle more complex problem by breaking them down into…

Simulation offers a promising approach for cheaply scaling training data for generalist policies. To scalably generate data from diverse and realistic tasks, existing algorithms either rely on large language models (LLMs) that may…

Competitive online games use rating systems to match players with similar skills to ensure a satisfying experience for players. In this paper, we focus on the importance of addressing different aspects of playing behavior when modeling…

Language models are now prevalent in software engineering with many developers using them to automate tasks and accelerate their development. While language models have been tremendous at accomplishing complex software engineering tasks,…

To address the challenge of limited experimental materials data, extensive physical property databases are being developed based on high-throughput computational experiments, such as molecular dynamics simulations. Previous studies have…

The largest experiments in machine learning now require resources far beyond the budget of all but a few institutions. Fortunately, it has recently been shown that the results of these huge experiments can often be extrapolated from the…