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.
Univideo: Unified understanding, generation, and editing for videos.arXiv preprint arXiv:2510.08377, 2025a
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
fields
cs.CV 9years
2026 9verdicts
UNVERDICTED 9representative citing papers
The PVIR benchmark tests video object removal on physical consistency using 95 annotated videos and shows that existing methods struggle with complex interactions like lingering shadows.
Current video models succeed on basic understanding but achieve under 25% success on logically grounded generation and near 0% on interactive generation, exposing gaps in multimodal reasoning.
VEFX-Bench releases a large human-labeled video editing dataset, a multi-dimensional reward model, and a standardized benchmark that better matches human judgments than generic evaluators.
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.
ImVideoEdit learns video editing from 13K image pairs by decoupling spatial modifications from frozen temporal dynamics in pretrained models, matching larger video-trained systems in fidelity and consistency.
Tuna-2 shows pixel embeddings can replace vision encoders in unified multimodal models, achieving competitive or superior results on understanding and generation benchmarks.
A multi-view prior-based framework for video object insertion that uses dual-path conditioning and an integration-aware consistency module to improve appearance stability and occlusion handling.
Mamoda2.5 is a 25B-parameter DiT-MoE unified AR-Diffusion model that reaches top video generation and editing benchmarks with 4-step inference up to 95.9x faster than baselines.
citing papers explorer
-
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.
-
Physics-Aware Video Instance Removal Benchmark
The PVIR benchmark tests video object removal on physical consistency using 95 annotated videos and shows that existing methods struggle with complex interactions like lingering shadows.
-
How Far Are Video Models from True Multimodal Reasoning?
Current video models succeed on basic understanding but achieve under 25% success on logically grounded generation and near 0% on interactive generation, exposing gaps in multimodal reasoning.
-
VEFX-Bench: A Holistic Benchmark for Generic Video Editing and Visual Effects
VEFX-Bench releases a large human-labeled video editing dataset, a multi-dimensional reward model, and a standardized benchmark that better matches human judgments than generic evaluators.
-
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.
-
ImVideoEdit: Image-learning Video Editing via 2D Spatial Difference Attention Blocks
ImVideoEdit learns video editing from 13K image pairs by decoupling spatial modifications from frozen temporal dynamics in pretrained models, matching larger video-trained systems in fidelity and consistency.
-
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation
Tuna-2 shows pixel embeddings can replace vision encoders in unified multimodal models, achieving competitive or superior results on understanding and generation benchmarks.
-
Controllable Video Object Insertion via Multiview Priors
A multi-view prior-based framework for video object insertion that uses dual-path conditioning and an integration-aware consistency module to improve appearance stability and occlusion handling.
-
Mamoda2.5: Enhancing Unified Multimodal Model with DiT-MoE
Mamoda2.5 is a 25B-parameter DiT-MoE unified AR-Diffusion model that reaches top video generation and editing benchmarks with 4-step inference up to 95.9x faster than baselines.