Aurora introduces a VLM-based agent that converts raw user video edit requests into structured conditioning inputs for a unified diffusion transformer, improving performance on underspecified tasks via a new benchmark.
VideoCoF: Unified Video Editing with Temporal Reasoner
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
abstract
Existing video editing methods face a critical trade-off: expert models offer precision but rely on task-specific priors like masks, hindering unification; conversely, unified temporal in-context learning models are mask-free but lack explicit spatial cues, leading to weak instruction-to-region mapping and imprecise localization. To resolve this conflict, we propose VideoCoF, a novel Chain-of-Frames approach inspired by Chain-of-Thought reasoning. VideoCoF enforces a ``see, reason, then edit" procedure by compelling the video diffusion model to first predict reasoning tokens (edit-region latents) before generating the target video tokens. This explicit reasoning step removes the need for user-provided masks while achieving precise instruction-to-region alignment and fine-grained video editing. Furthermore, we introduce a RoPE alignment strategy that leverages these reasoning tokens to ensure motion alignment and enable length extrapolation beyond the training duration. We demonstrate that with a minimal data cost of only 50k video pairs, VideoCoF achieves state-of-the-art performance on VideoCoF-Bench, validating the efficiency and effectiveness of our approach. Our code, weight, data are available at https://github.com/knightyxp/VideoCoF.
citation-role summary
dataset 1
citation-polarity summary
years
2026 8verdicts
UNVERDICTED 8roles
dataset 1polarities
background 1representative citing papers
GeoEdit introduces a Lift-Manipulate-Render-Denoise pipeline with dual-branch denoising and variance-homogeneous injection for 3D-consistent object editing in single photos.
SpongeBob introduces the first end-to-end audio-visual joint editing framework using sync-aware bidirectional attention and context-aware modules, plus a new dataset and benchmark, claiming 30% Sync-C and 12.5% Ctx-F1 gains over baselines.
MiVE repurposes VLMs as multiscale feature extractors integrated into a unified self-attention Diffusion Transformer for reference-guided video editing, claiming top human preference scores over prior methods.
LIVE achieves state-of-the-art instruction-based video editing by jointly training on image and video data with a frame-wise token noise strategy to bridge domain gaps and a new benchmark of over 60 tasks.
A new keyframe selection framework combines structural, tracking, and semantic criteria to select reliable anchor frames for diffusion-based video editing under occlusion.
EasyVFX decouples VFX generation via frequency-aware Mixture-of-Experts and test-time training to achieve realistic effects with limited resources.
Reasoning in language models should be measured by the faithfulness and validity of their multi-step search processes and intermediate traces, not final-answer accuracy.
citing papers explorer
-
LIVE: Leveraging Image Manipulation Priors for Instruction-based Video Editing
LIVE achieves state-of-the-art instruction-based video editing by jointly training on image and video data with a frame-wise token noise strategy to bridge domain gaps and a new benchmark of over 60 tasks.