arXiv AI
Error-Subspace Calibration for Multi-Task Model Merging
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
Hugging Face Trending Papers
Jun 25
Learning to Recover Task Experts from a Multi-Task Merged Model
Multi-task model merging aims to consolidate several task-specific experts into a unified model, yet static merging consistently suffers from parameter interference. While dynamic merging models aim to bridge this gap, many works rely on the costly storage and loading of redundant expert components at inference.
arXiv AI
Jun 26
Learning to Recover Task Experts from a Multi-Task Merged Model
arXiv:2606. 26902v1 Announce Type: new Abstract: Multi-task model merging aims to consolidate several task-specific experts into a unified model, yet static merging consistently suffers from parameter interference.
arXiv Machine Learning
Jun 18
PACT: Preserving Anchored Cores in Task-vectors for Model Merging
arXiv:2606. 18627v1 Announce Type: new Abstract: Model merging has emerged as a training-free alternative to multi-task learning, aiming to combine multiple task-specific fine-tuned models into a single multi-task model.
arXiv AI
Jun 18
Essential Subspace Merging for Multi-Task Learning
arXiv:2606. 19164v1 Announce Type: cross Abstract: Model merging aims to enable multi-task learning by integrating the capabilities of multiple models fine-tuned from the same pre-trained checkpoint into a single model.
arXiv Computation and Language
Oct 22
GRAM: Group-wise Rank-Aware Model Merging via Subspace Alignment
arXiv:2610.29110v1 Announce Type: cross Abstract: Merging different models into a single model is highly desirable for multi-task deployment, particularly in regulated domains like healthcare. In suc...
arXiv Computer Vision
5d ago
CRLoMTL: Conflict-Resolution through Low-rank matrices for Multi-Task Learning
CRLoMTL is a parameter‑efficient multi‑task learning framework that mitigates task interference by operating in a low‑rank parameter‑update space rather than gradient space. It learns task‑specific LoRA updates and fuses them through a shared‑subspace resolver based on singular value decomposition, producing a single deployment‑time update that can be folded into the backbone. Experiments on Swin Transformer backbones across PASCAL‑Context, NYUD‑v2, and CelebA show that CRLoMTL improves accuracy over single‑task baselines while training only a small fraction of the parameters.