← Search

Hoai-Chau Tran

2 accepted papers

2025

How Many Tokens Do 3D Point Cloud Transformer Architectures Really Need?

NeurIPS 2025poster

Recent advances in 3D point cloud transformers have led to state-of-the-art results in tasks such as semantic segmentation and reconstruction. However, these models typically rely on dense token representations, incurring high computational and memory costs during training and inference. In this wor…

Cited by 0SourcecodeScholar
2024

Accelerating Transformers with Spectrum-Preserving Token Merging

NeurIPS 2024poster

Increasing the throughput of the Transformer architecture, a foundational component used in numerous state-of-the-art models for vision and language tasks (e.g., GPT, LLaVa), is an important problem in machine learning. One recent and effective strategy is to merge token representations within Trans…