VLM-to-DiT alignment in video editing models acts as a semantic bottleneck that degrades fine-grained structural semantics, demonstrated via a new diagnostic dataset and protocol on relation-based edits.
Instructx: Towards unified visual editing with mllm guidance.https://arxiv.org/abs/2510.08485
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
Sparkle supplies a large-scale dataset and benchmark for instruction-driven video background replacement, enabling models that generate more natural and temporally consistent new scenes than earlier approaches.
VideoCoF adds an explicit reasoning step using edit-region latents in video diffusion models to enable precise mask-free editing and motion alignment with only 50k training pairs.
InsEdit adapts a video diffusion backbone for text-instruction video editing via Mutual Context Attention, achieving SOTA open-source results with O(100K) data while also supporting image editing.
citing papers explorer
-
What Semantics Survive the Connector? Diagnosing VLM-to-DiT Alignment in Video Editing
VLM-to-DiT alignment in video editing models acts as a semantic bottleneck that degrades fine-grained structural semantics, demonstrated via a new diagnostic dataset and protocol on relation-based edits.
-
Sparkle: Realizing Lively Instruction-Guided Video Background Replacement via Decoupled Guidance
Sparkle supplies a large-scale dataset and benchmark for instruction-driven video background replacement, enabling models that generate more natural and temporally consistent new scenes than earlier approaches.
-
VideoCoF: Unified Video Editing with Temporal Reasoner
VideoCoF adds an explicit reasoning step using edit-region latents in video diffusion models to enable precise mask-free editing and motion alignment with only 50k training pairs.
-
InsEdit: Towards Instruction-based Visual Editing via Data-Efficient Video Diffusion Models Adaptation
InsEdit adapts a video diffusion backbone for text-instruction video editing via Mutual Context Attention, achieving SOTA open-source results with O(100K) data while also supporting image editing.