AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Cross-Tactile Sensor Representation Learning

Yan Zhang, Zheng WANG, Pengpeng Zeng, Xing Xu, Jingkuan Song, Heng Tao Shen

ICML 2026 · Vision-language and multimodal › Cross-modal learning · approach: Unimodal-to-multimodal representation transfer

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 Cross-Sensor Modulator (CSM) (ablation)CTSRL Stage 1 · SITR Bench DIGIT-Miniaccuracy: 78.16 -> 80.62Improved
add cross-sensor alignment loss (ablation)CTSRL Stage 1 · SITR Bench DIGIT-Miniaccuracy: 74.34 -> 80.62Improved
add intra-sensor loss (ablation)CTSRL Stage 1 · SITR Bench DIGIT-Miniaccuracy: 73.70 -> 80.62Improved
add loss normalization (ablation)CTSRL Stage 1 · SITR Bench DIGIT-Miniaccuracy: 26.02 -> 80.62Improved
add cross-sensor alignment on top of normalized loss versus plain Barlow Twins (ablation)CTSRL Stage 1 · SITR Bench DIGIT-Miniaccuracy: 23.84 -> 80.62Improved
add intra-sensor loss (ablation)CTSRL Stage 1 · SITR Bench no-transferaccuracy: 99.62 -> 99.58No clear effect
add CSM (ablation)CTSRL Stage 2 · OF Realaccuracy: 48.70 -> 50.14Improved
add Stage 1 cross-sensor pretraining (ablation)CTSRL Stage 2 · OF Realaccuracy: 46.88 -> 50.14Improved
freeze the CLIP vision encoder (ablation)CTSRL Stage 2 · Cloth materialaccuracy: 41.98 -> 48.33Improved
add language modality alignment (ablation)CTSRL Stage 2 · OF Realaccuracy: 34.09 -> 50.14Improved
add vision modality alignment (ablation)CTSRL Stage 2 · OF Realaccuracy: 46.02 -> 50.14Improved
add Stage 2 cross-modal semantic alignment after Stage 1CTSRL · Touch and Go materialaccuracy: 56.42 -> 87.70Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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