The paper introduces WaterBird-Edit, a benchmark that separates bird habitat labels from background context to detect evidence misgrounding in multimodal knowledge editing. It proposes VICE, a retrieval‑based framework that stores edits in external memory and uses visual in‑context demonstrations to focus on task‑relevant evidence. Experiments on three benchmarks show VICE improves lifelong editing performance and reduces sensitivity to background changes on WaterBird-Edit.
arXiv:2607. 01978v1 Announce Type: new Abstract: Online multimodal knowledge editing requires injecting a continual stream of visual-textual corrections into multimodal large language models (MLLMs) with bounded overhead and minimal disruption to unrelated behaviors.
arXiv:2607. 21318v1 Announce Type: cross Abstract: Replacing an object with one that differs in category or shape requires complete source removal, natural target formation unconstrained by the source silhouette, and preservation of unrelated content.
Replacing an object with one that differs in category or shape requires complete source removal, natural target formation unconstrained by the source silhouette, and preservation of unrelated content. Existing training-free editors either localize edits from terminal predictions under source and target prompts or preserve unrelated content through spatially unselective source-feature reuse without explicit region discovery.
arXiv:2608.16745v2 Announce Type: replace Abstract: Despite remarkable progress in instruction-based video editing, textual descriptions remain limited in expressing fine-grained appearance, spatial...
arXiv:2608. 07565v1 Announce Type: cross Abstract: Conversational assistants increasingly recommend follow-up edits to help users continue a task.
arXiv:2610.01670v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are increasingly used as automated judges for instruction-based image editing and as reward signals for model...
The paper introduces RISEBench and its expanded version RISEBench++, a benchmark for evaluating reasoning-informed visual editing (RISE). RISEBench++ categorizes tasks into six reasoning dimensions—Temporal, Causal, Spatial, Logical, Counterfactual, and Hybrid—decomposed into 12 subcategories and 65 fine-grained task types, and includes 1,000 human‑annotated test cases in English and Chinese. The authors also present RISE‑Agent, a training‑free framework that integrates reasoning‑driven planning, tool‑augmented execution, and verifier‑guided refinement, outperforming most existing approaches on diverse RISE tasks.
ReasonEdit is a new editor for vision‑language models that allows users to provide reasoning explanations during the editing process. It stores human reasoning in a codebook and retrieves relevant facts at inference time using a topology‑balanced multimodal embedding approach inspired by network science. Experiments on four VLMs and multiple rationale‑based visual question answering datasets show that incorporating human reasoning leads to state‑of‑the‑art editing performance and better generalization.
The paper investigates how visual interventions—training‑free edits applied to multimodal large language models—affect hallucinations and prediction quality. By applying a visual‑residual edit across successive decoder layers and matching its RMS strength, the authors identify an Evidence Anchoring Boundary (EAB) where the intervention’s influence drops sharply; effects before the EAB are 13.78–26.10× larger than after it. They further compare counterfactual subtraction across different question types and introduce calibrated selective routing, which only alters predictions when calibration supports an intervention, improving attribute accuracy by 1.56–1.81 percentage points while avoiding the harms of universal subtraction.
arXiv:2607. 07051v1 Announce Type: cross Abstract: Conversational image editing requires preserving not only visible content, but also content that temporarily disappears across turns.
arXiv:2606. 05950v1 Announce Type: new Abstract: Text-guided image editing has advanced rapidly with diffusion models and unified multimodal foundation models.
arXiv:2610.33841v1 Announce Type: cross Abstract: When an image and its caption disagree, can a user reliably control which one a vision-language model (VLM) follows? Accuracy alone cannot answer thi...