arXiv Computer Vision October 12, 2026 By Alex Junho Lee

ROSETTA: Rotation Subspace Estimation for Training-free Transmodal Alignment

Read the original on arXiv Computer Vision →

ROSETTA is a training‑free calibration layer that aligns feature spaces from independently trained encoders by estimating a local rotation in whitened space. It relies on the observation that the relative transformation between any two such systems is a spatially preserving rotation whose angular velocity behaves like white noise, and that the cross‑covariance between encoder outputs has low effective rank, making local alignment tractable. The method uses an expectation‑maximization procedure and requires no co‑observation at query time, achieving milliseconds overhead per query on three public driving datasets across LiDAR, camera, thermal, and event modalities.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Hugging Face Trending Papers

Jun 23

REDI-Match: Rotation-Equivariant Distillation for Efficient and Robust Dense Matching

Vision Foundation Models (VFMs) have significantly advanced dense feature matching, yet severe in-plane rotation remains a critical challenge. Existing solutions face a fundamental dilemma: data-driven methods require inefficient parameter scaling to implicitly learn rotations, whereas strictly equivariant networks lack the semantic capacity of modern VFMs.

efficiency benchmarks safety

arXiv Machine Learning

Sep 23

GINIO: A Geometric SO(3)-Equivariant Interface for Neural Inertial Odometry

GINIO is a geometric SO(3)-equivariant interface designed for neural inertial odometry that ensures learned measurements transform consistently under any IMU mounting convention. It predicts motion measurements and uncertainties that obey vector and tensor transformation laws, and introduces Last-Frame Alignment to enable efficient sensor-frame learning equivalent to world-frame training. The interface is instantiated in several architectures—filter-connected NIO, AirIO-style recurrent aerial prediction, EqNIO-style full-SO(3) canonicalization, and ResNet-style temporal backbones—achieving significant accuracy and efficiency gains across multiple benchmarks.

By Chankyo Kim, Minghan Zhu, Tzu-Yuan Lin, Avantika Rattan, Maani Ghaffari

safety

arXiv AI

Jun 17

Robustness of Similarity-based Positional Encoding Under Rotations: Theoretical Analysis and Experimental Validation

arXiv:2606. 17961v1 Announce Type: cross Abstract: Positional encoding is a fundamental component of Transformer architectures, as it injects information about the spatial or sequential arrangement of inputs.

By Andrea Santomauro, Luigi Portinale, Giorgio Leonardi

llms computer-vision benchmarks

arXiv Computer Vision

Aug 31

GAAT: Geometry-Aware Alignment Transformer for Multimodal UAV Perception

arXiv:2608.27971v1 Announce Type: new Abstract: Unmanned aerial vehicle (UAV) multimodal perception integrates visible (RGB), infrared (IR), synthetic aperture radar (SAR), and depth sensors for scen...

By Jingpu Yang, Debin Tang, Yilin Sun, Fengxian Ji, Jiahua Zhu, Wenrui Ding, Yufeng Wang

llms nlp multimodal benchmarks safety

arXiv Computer Vision

Oct 2

PAGER: Partial-to-global Alignment via Geometric and Relational Distillation

PAGER is a label‑free adaptation method that aligns partial, viewpoint‑dependent 3D observations with a frozen global semantic space. It uses matched‑point feature alignment and relational supervision to anchor partial features to their global counterparts while preserving similarity structure, all without altering the pretrained encoder or global probe. Experiments show PAGER outperforms label‑supervised PEFT on Sonata and Concerto, and achieves superior zero‑shot transfer from ScanNet to ScanNet++ compared to fully fine‑tuned Sonata.

By Akira-Miranda Adeyomi Adeniran-Lowe, Binod Singh, Lars Arnold Dethlefsen, Lazaros Nalpantidis, Theodora Kontogianni

computer-vision robotics fine-tuning efficiency benchmarks safety

arXiv AI

Oct 1

Template-Search Domain Adaptation via Multi-Stage Feature Alignment for Cross-Modal Object Tracking

The paper introduces TSDA-Track, a Template-Search Domain Adaptation framework designed to reduce modality gaps in cross‑modal visual object tracking. Two variants are explored: Pre‑AFA TSDA‑Track uses adversarial alignment before transformer interaction, while Enc‑CFA TSDA‑Track applies contrastive alignment after interaction to strengthen cross‑modal correspondence. Experiments on datasets such as LasHeR, RGBT234, GTOT, and Anti‑UAV‑024 show that both variants outperform state‑of‑the‑art trackers, with Pre‑AFA achieving an SR/PR of 43.2/56.0 on RGBT234 under the modality‑switch protocol.

By Fereshteh Aghaee Meibodi, Amir Mehdi Soufi Enayati, Shadi Alijani, Homayoun Najjaran

llms fine-tuning multimodal benchmarks safety