UniVideo: Unified Understanding, Generation, and Editing for Videos
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:WCNPFGM5record.jsonopen to challenge →
read the original abstract
Unified multimodal models have shown promising results in multimodal content generation and editing but remain largely limited to the image domain. In this work, we present UniVideo, a versatile framework that extends unified modeling to the video domain. UniVideo adopts a dual-stream design, combining a Multimodal Large Language Model (MLLM) for instruction understanding with a Multimodal DiT (MMDiT) for video generation. This design preserves the MLLM's original text generation capabilities, enables accurate interpretation of complex multimodal instructions, and maintains visual consistency in the generated content. Built on this architecture, UniVideo unifies diverse video generation and editing tasks under a single multimodal instruction paradigm and is jointly trained across them. Extensive experiments demonstrate that UniVideo matches or surpasses state-of-the-art task-specific baselines in text/image-to-video generation, in-context video generation and in-context video editing. Notably, the unified design of UniVideo enables two forms of generalization. First, UniVideo supports task composition, such as combining editing with style transfer, by integrating multiple capabilities within a single instruction. Second, even without explicit training on free-form video editing, UniVideo transfers its editing capability from large-scale image editing data to this setting, handling unseen instructions such as changing the environment or altering materials within a video. Beyond these core capabilities, UniVideo also supports visual-prompt-based video generation, where the MLLM interprets visual prompts and guides the MMDiT during synthesis. To foster future research, we released our model and code.
This paper has not been read by Pith yet.
Forward citations
Cited by 26 Pith papers
-
MotiMotion: Motion-Controlled Video Generation with Visual Reasoning
MotiMotion adds visual reasoning via a training-free VLM to refine primary trajectories and hallucinate secondary motions, plus a confidence-aware guidance scheme, yielding more plausible interactions on the new MotiB...
-
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.
-
Aurora: Unified Video Editing with a Tool-Using Agent
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.
-
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.
-
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.
-
SteerVTE: Seamless Video Text Editing with Style and Glyph Control
SteerVTE adds lightweight style and dual-granularity glyph adapters to a frozen video diffusion model, introduces a glyph-aware loss and progressive training, and releases a 1M synthetic dataset to enable accurate vid...
-
AlbedoEdit: Unified Instance-Level Video Editing with Albedo Guidance
AlbedoEdit fine-tunes video foundation models to translate RGB videos into edited versions conditioned on user-edited first-frame albedo maps, trained on a new synthetic paired dataset for insertion, removal, and text...
-
Lumos-Nexus: Efficient Frequency Bridging with Homogeneous Latent Space for Video Unified Models
Lumos-Nexus is a training-efficient video generation framework using two-stage alignment of a lightweight model followed by progressive frequency bridging to a high-fidelity generator in homogeneous latent space, plus...
-
What Semantics Survive the Connector? Diagnosing VLM-to-DiT Alignment in Video Editing
Introduces TRACE-Edit dataset and evaluation protocol demonstrating semantic degradation of structural variables during VLM-to-DiT alignment in flow-matching video editors.
-
Lance: Unified Multimodal Modeling by Multi-Task Synergy
Lance presents a dual-stream mixture-of-experts model with modality-aware positional encoding and staged multi-task training that outperforms prior open-source unified models on image and video generation while keepin...
-
LIVEditor-14B: Lightning Unified Video Editing via In-Context Sparse Attention
LIVEditor-14B applies a new sparse attention method (ISA) that prunes context and uses query-sharpness routing to cut attention latency ~60% with no loss in editing quality on standard benchmarks.
-
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation
Tuna-2 shows that direct pixel embeddings can replace vision encoders in unified multimodal models, achieving competitive generation and stronger understanding at scale.
-
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.
-
LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokens
LLaMo scales pretrained LLMs for unified motion-language tasks by encoding motion into continuous causal latents and adding a flow-matching head for real-time autoregressive generation and captioning.
-
Bridging Video Understanding and Generation in a Unified Framework
Vega unifies video understanding and generation via shared vocabulary and hybrid autoregressive-diffusion architecture, reporting strong results on VBench and VideoMME.
-
Smart-Insertion-V: Photorealistic Video Insertion via a Closed-Loop Feedback Dual-Stream Framework
Smart-Insertion-V is a dual-stream closed-loop framework with Dual-World-View RoPE and a Decoupled Guidance Module that inserts reference objects into videos while achieving stylistic harmony despite domain gaps.
-
Bernini: Latent Semantic Planning for Video Diffusion
Bernini is a framework that uses an MLLM planner to output semantic representations for a DiT renderer to generate or edit videos, reporting SOTA benchmark performance.
-
Lance: Unified Multimodal Modeling by Multi-Task Synergy
Lance introduces a dual-stream MoE model with modality-aware rotary positional encoding and staged multi-task training that outperforms open-source unified models on image and video generation while retaining understa...
-
LIVEditor-14B: Lightning Unified Video Editing via In-Context Sparse Attention
ISA prunes low-saliency context tokens and routes queries by sharpness to either full or 0-th order Taylor sparse attention, enabling LIVEditor to cut attention latency ~60% while beating prior video editing methods o...
-
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.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.