CRLoMTL: Conflict-Resolution through Low-rank matrices for Multi-Task Learning
arXiv:2610.36337v1 Announce Type: new Abstract: Multi-task learning (MTL) improves model efficiency by sharing representations across related vision tasks, but it often suffers from negative transfer when task updates interfere with one another. Existing conflict-mitigation methods typically operat…
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-10-28 04:00 · arXiv cs.CV
CRLoMTL: Conflict-Resolution through Low-rank matrices for Multi-Task Learning