Cross-Modal Forgetting and Transfer in Unified Multimodal Post-Training
arXiv:2610.23918v1 Announce Type: new Abstract: Unified multimodal models answer questions about images and also generate images with one shared set of weights. This creates a post-training risk that single-purpose models do not have: fine-tuning one capability can damage another that works in a di…
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-10-20 04:00 · arXiv cs.CV
Cross-Modal Forgetting and Transfer in Unified Multimodal Post-Training