DT-LoRA: Reaching Beyond the Tangent Space of Low-Rank Adaptation

arXiv:2610.17730 · cs.CV, cs.LG · Submitted 2026-10-13 · Read on arXiv

cs.CV, cs.LG

Submitted: 2026-10-13

Updated: 2026-10-13

Comments: 16 pages, 2 figures, 11 tables. Code: https://github.com/Snipine/DT-LoRA

Code: https://github.com/Snipine/DT-LoRA

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Adaptation — 1× in this paper · explained in 1 episode

Sources

• MMDetection: Open MMLab Detection Toolbox and Benchmark
• EVA-CLIP: Improved Training Techniques for CLIP at Scale
• A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models