AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

SVL: Empowering Spiking Neural Networks for Efficient 3D Open-World Understanding

Xuerui Qiu, Shaowei Gu, Peixi Wu, JiaKui Hu, Yaozhi Wen, Yuqi Pan, Xinhao Luo, Bo XU, Guoqi Li

ICML 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Open-vocabulary alignment from VLMs

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
add spike-image NCE alignment to no-alignment baseline (ablation)SVL pretraining (E-3DSNN-T) · Objaverse-LVIS zero-shottop-1 accuracy (%): 0.5 -> 24.8Improved
add spike-text NCE alone (no image alignment) (ablation)SVL pretraining (E-3DSNN-T) · Objaverse-LVIS zero-shottop-1 accuracy (%): 0.5 -> 21.9Improved
combine spike-text NCE with spike-image NCE (ablation)SVL pretraining (E-3DSNN-T) · Objaverse-LVIS zero-shottop-1 accuracy (%): 24.8 -> 31.7Improved
add fine-grained spike-image MSE loss (ablation)SVL pretraining (E-3DSNN-T) · Objaverse-LVIS zero-shottop-1 accuracy (%): 31.7 -> 33.6Improved
add fine-grained spike-image MSE loss (ablation)SVL pretraining (E-3DSNN-T) · ModelNet40 zero-shottop-1 accuracy (%): 77.8 -> 79.6Improved
increase pretraining T from 2 to 4 at D=1 (ablation)SVL pretraining (E-3DSNN-T) · Objaverse-LVIS zero-shottop-1 accuracy (%): 32.7 -> 32.9No clear effect
increase firing bits D from 2 to 4 at T=1 (ablation)SVL pretraining (E-3DSNN-T) · Objaverse-LVIS zero-shottop-1 accuracy (%): 32.9 -> 33.6Improved
use larger OpenCLIP image encoder (ViT-B to ViT-bigG) for prototypes (ablation)SVL pretraining · ModelNet40 zero-shottop-1 accuracy (%): 66.8 -> 79.6Improved
use larger OpenCLIP image encoder (ViT-B to ViT-bigG) for prototypes (ablation)SVL pretraining · Objaverse-LVIS zero-shottop-1 accuracy (%): 25.1 -> 33.6Improved
raise voxel size from 0.01 to 0.02 (0.04 gives 79.1) (ablation)E-3DSNN-T + SVL · ModelNet40 zero-shottop-1 accuracy (%): 78.9 -> 79.6Mixed
raise input points from 10k to 20k (ablation)E-3DSNN-T + SVL · ModelNet40 zero-shottop-1 accuracy (%): 79.6 -> 79.8No clear effect
add SVL pretraining to Spike PointNet (ablation)Spike PointNet · ScanObjectNN fine-tunedaccuracy (%): 70.0 -> 76.1Improved

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