2 papers
cs.CV2026
Point-Selection Fine-Tuning Framework for Robust Point Cloud Classification
Da Li, Chang Ma, Dongfu Yin
Noisy and corrupted points can substantially degrade point cloud recognition performance, especially under challenging corruption settings. In particular, full fine-tuning of 3D pr…
cs.DC2026
A Training-Memory Regression in MLA Sequence Parallelism: Why Megatron-Core Forbids Absorption, and LAGA -- a Communication-Efficient Fix
Changzheng Ma
Multi-head Latent Attention (MLA) ships two implementations in Megatron-Core: an explicit form used for training and an absorbed form -- which slashes collective communication by g…