AI Paper Atlas

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

One Model to Translate Them All: Universal Any-to-Any Translation for Heterogeneous Collaborative Perception

Yang Li, Weize Li, Quan Yuan, Shao Congzhang, Guiyang Luo, Yunqi Ba, Xuanhan Zhu, Xinyuan Ding, Xiaoyuan Fu, Jinglin Li

ICML 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 0 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
add contrastive loss L_IC in stage 1 (ablation)UniTrans · OPV2V-HAP@0.5 / AP@0.7: 0.685/0.575 -> 0.716/0.605Improved
add modality classification loss L_IS in stage 1 (ablation)UniTrans · OPV2V-HAP@0.5 / AP@0.7: 0.694/0.583 -> 0.716/0.605Improved
add stage 1 intrinsic-space training (both L_IC and L_IS) (ablation)UniTrans · OPV2V-HAP@0.5 / AP@0.7: 0.662/0.540 -> 0.716/0.605Improved
add downstream task loss L_task (ablation)UniTrans · OPV2V-HAP@0.5 / AP@0.7: 0.691/0.579 -> 0.716/0.605Improved
add feature distillation loss L_feat (ablation)UniTrans · OPV2V-HAP@0.5 / AP@0.7: 0.653/0.531 -> 0.716/0.605Improved
add routing contrastive loss L_ctr (ablation)UniTrans · OPV2V-HAP@0.5 / AP@0.7: 0.688/0.576 -> 0.716/0.605Improved
add router load-balancing/logit regularizer L_r (ablation)UniTrans · OPV2V-HAP@0.5 / AP@0.7: 0.708/0.598 -> 0.716/0.605Improved
replace Classic MoE (multi-expert forwarding, TopK=3) with parameter-combination single translatorUniTrans · OPV2V-H profilingGFLOPs: 245.5 -> 109.3Improved
mapping inferred in intrinsic latent space instead of routing directly on high-dim features (vs Classic MoE)UniTrans · OPV2V-HAP@0.5 / AP@0.7 avg: 0.653/0.544 -> 0.716/0.605Improved
UniTrans vs best baseline on camera ego modalitiesUniTrans · OPV2V-H m27 / m30AP@0.5/AP@0.7: 0.497/0.243 on m27, 0.406/0.202 on m30Improved
UniTrans vs NegoCollab in real-world settingUniTrans · DAIR-V2XAP@0.5/AP@0.7 avg: 0.509/0.389 -> 0.553/0.421Improved

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