ICLR "long-context understanding" Papers
2 papers found
NovelQA: Benchmarking Question Answering on Documents Exceeding 200K Tokens
Cunxiang Wang, Ruoxi Ning, Boqi Pan et al.
ICLR 2025posterarXiv:2403.12766
23
citations
World Model on Million-Length Video And Language With Blockwise RingAttention
Hao Liu, Wilson Yan, Matei Zaharia et al.
ICLR 2025oralarXiv:2402.08268
144
citations