2 papers
cs.CL2026
OnlineQAT: On-Policy Distillation for Ultra-Low-Bit Large Language Models
Wenjun Wang, Heng Li, Yanggan Gu +1
Quantization-aware training (QAT) can recover much of the accuracy lost when large language models are compressed below four bits. Existing re- covery stages, however, are commonly…
cs.CV2025
HccePose(BF): Predicting Front & Back Surfaces to Construct Ultra-Dense 2D-3D Correspondences for Pose Estimation
Yulin Wang, Mengting Hu, Hongli Li +1
In pose estimation for seen objects, a prevalent pipeline involves using neural networks to predict dense 3D coordinates of the object surface on 2D images, which are then used to…