Differential Vector Erasure: Unified Training-Free Concept Erasure for Flow Matching Models

arXiv:2602.01089 · cs.CV · Submitted 2026-02-01 · Read on arXiv

cs.CV

Submitted: 2026-02-01

Updated: 2026-10-30

Terminology

• Flow Matching — 3× in this paper · explained in 23 episodes
• Flow Matching Model — 3× in this paper · explained in 3 episodes
• Differential Vector Erasure — 2× in this paper
• Diffusion Model — 2× in this paper · explained in 10 episodes
• Diffusion Models — 2× in this paper · explained in 9 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• Dreaming in Flow: Bidirectional Self-Refinement for Unified Multimodal Models
• Vorch-IR: Long-Form Unified Multimodal Identity Replacement Video Generation
• WorldMesh: Generating Navigable Multi-Room 3D Scenes via Mesh-Conditioned Image Diffusion
• OctWorld: Long-Range World-Consistent Video Generation with Octree-Based 3D Mapping
• Vorch-Streamer: Extending Human Audio-Visual Generation to Real-Time Long-Form Streaming