AI Paper Atlas

Research map / Point clouds / Point cloud classification

Exploring the Potential of Encoder-free Architectures in 3D LMMs

Yiwen Tang, Ziyu Guo, Zhuhao Wang, Renrui Zhang, Qizhi Chen, Junli Liu, Delin Qu, Dong Wang, Bin Zhao, Xuelong Li

ICLR 2026 · Point clouds › Point cloud classification · approach: Point-language and open-vocabulary 3D · 11 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
remove the 3D encoder with the original token embedding (ablation)PointLLM · Objaverse classificationGPT-4 score: decrease of 17.5%Hurt
remove the 3D encoder with the original token embedding (ablation)PointLLM · Objaverse captioningGPT-4 score: decrease of 10.48%Hurt
add Hybrid Semantic Loss in pre-training (ablation)encoder-free ENEL-7B · Objaverse captioningGPT-4 score: 47.19 -> 50.92Improved
add Hybrid Semantic Loss in pre-training (ablation)encoder-free ENEL-7B · Objaverse classificationGPT-4 score: 50.61 -> 55.00Improved
add contrastive loss in pre-training (ablation)encoder-free 3D LMM · Objaverse classificationGPT-4 score: 47.90 -> 42.50Hurt
use knowledge distillation loss from Uni3D (ablation)encoder-free 3D LMM · Objaverse captioningGPT-4 score: 43.50 -> 43.87No clear effect
raise mask ratio from 30% to 60% for masked modeling (ablation)encoder-free 3D LMM · Objaverse captioningGPT-4 score: 45.20 -> 43.64Hurt
add masked modeling loss on patches (30% mask) (ablation)encoder-free 3D LMM · Objaverse classificationGPT-4 score: 47.90 -> 49.00Improved
add gated self-attention in geometry aggregation (ablation)ENEL-7B · Objaverse classificationGPT-4 score: 53.50 -> 55.00Improved
add gated self-attention in geometry aggregation (ablation)ENEL-7B · Objaverse captioningGPT-4 score: 49.26 -> 50.92Improved
increase LLM layers H between aggregation and propagation to 4 or 8 (ablation)ENEL-7B · ObjaverseGPT-4 score: H=2 best (54.25 classification, 49.56 captioning)Hurt
use 13B Vicuna instead of 7BENEL · Objaverse captioningGPT-4 score: 51.03 -> 53.24Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy