Large Language Models (LLMs) have shown impressive performance on a wide range of generative tasks. Yet their probabilistic nature makes them, in isolation, fundamentally unsuited for industrial product configuration, where outputs must be syntactically valid, semantically consistent with a knowledge base of hundreds o...
Danilo Valerio, Philipp Kogler, Stefan Bischof et al.· 0 citations
LLMZero, an agentic system that optimizes training trajectories via tree search by diagnosing pathologies at each checkpoint and proposing coordinated multi-parameter transitions, discovers strategies that improve over the base model and over grid search and over grid search, consistently outperforming random search an...
Haoyang Fang, Wei Zhu, Boran Han et al.· arXiv.org· 2 citations
SD-MAR (Synthetic Data for Multi-image Analytical Reasoning) is introduced, a framework for training and evaluating VLMs on multi-image analytical reasoning that constructs paired visual scenarios through controlled perturbations and generates reasoning tasks spanning semantic change attribution and quantitative compar...
Shiyu Yuan, Sourav S. Bhabesh, Zhe Wang et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.