conftrace_

token shuffling

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

global-local distillation (1) state of the art (1) masked autoencoding (1) video encoder (1) long-context learning (1) language model pretraining (1) long-context training (1) language model (1) pretraining (1) data augmentation (1)

Papers

Untie the Knots: An Efficient Data Augmentation Strategy for Long-Context Pre-Training in Language Models ACL 2025 VideoPrism: A Foundational Visual Encoder for Video Understanding ICML 2024