Author name: Austin Veselka

arXiv:2604.02371v1 Announce Type: new
Abstract: Visual long-document understanding is critical for enterprise, legal, and scientific applications, yet the best performing open recipes have not explored reasoning, a capability which has driven leaps in…

arXiv:2602.15257v2 Announce Type: replace-cross
Abstract: We present the first comprehensive, large-scale study of training long-context vision language models up to 344K context, targeting long-document visual question answering with measured transfe…