conftrace_

hybrid mamba-transformer

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

4d perception (1) masked auto-regressive pretraining (1) long video (1) autoregressive pretraining (1) hybrid architecture (1) long video understanding (1) vision backbone (1) masked autoencoder (1) mamba model (1) state-of-the-art performance (1)

Papers

PointNet4D: A Lightweight 4D Point Cloud Video Backbone for Online and Offline Perception in Robotic Applications WACV 2026 MAP: Unleashing Hybrid Mamba-Transformer Vision Backbone's Potential with Masked Autoregressive Pretraining CVPR 2025 Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers ICCV 2025