Found 4 document(s)
Page 1 of 1
-
Preference optimization can improve every ranking metric while building a hidden, shared representation shift that the relative loss barely sees, one that can eventually destroy generation. We trace this failure to the c...
-
Diffusion trajectory planners with domain-specific experts face a practical question in unseen regions: can they rely on selecting among existing experts, or must the planner itself adapt? We study this question using a ...
-
Large Language Models (LLMs) have shown remarkable capabilities across tasks, but they still struggle with complex reasoning that requires integrating scattered knowledge. Graph Retrieval-Augmented Generation (GraphRAG) ...
-
We develop non-Archimedean techniques to analyze the degeneration of the dynamics of a sequence of holomorphic maps of the Riemann sphere.Given any sequence of rational maps f_n of degree d at least 2, we construct in th...