3 papers
cs.LG2025
Filtering Learning Histories Enhances In-Context Reinforcement Learning
Weiqin Chen, Xinjie Zhang, Dharmashankar Subramanian +1
Transformer models (TMs) have exhibited remarkable in-context reinforcement learning (ICRL) capabilities, allowing them to generalize to and improve in previously unseen environmen…
cs.CV2025
PvNeXt: Rethinking Network Design and Temporal Motion for Point Cloud Video Recognition
Jie Wang, Tingfa Xu, Lihe Ding +3
Point cloud video perception has become an essential task for the realm of 3D vision. Current 4D representation learning techniques typically engage in iterative processing coupled…
cs.CL2025
MiniMax-01: Scaling Foundation Models with Lightning Attention
MiniMax, Aonian Li, Bangwei Gong +87
We introduce MiniMax-01 series, including MiniMax-Text-01 and MiniMax-VL-01, which are comparable to top-tier models while offering superior capabilities in processing longer conte…