A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Toby Simonds
This paper introduces RocketBench, a benchmark connecting LLMs to high-fidelity rocket simulations, and shows that RL-enhanced 7B LLMs outperform both SoTA foundation models and human experts in engineering design tasks.
Unknown
This paper presents the first data scaling law for generative world models in embodied settings, uncovering how data volume impacts simulation fidelity and downstream policy learning.
Unknown
mmE5 is a multimodal multilingual embedding model trained on synthetic data via a framework that ensures broad task/language coverage, robust cross-modal alignment, and high fidelity through self-evaluation and refinement.
Unknown
This paper investigates whether large language models can serve as implicit text-based world models, proposing evaluation metrics for fidelity and coherence.