REVIEW 13 cited by
FullDiT: Multi-Task Video Generative Foundation Model with Full Attention
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
FullDiT: Multi-Task Video Generative Foundation Model with Full Attention
read the original abstract
Current video generative foundation models primarily focus on text-to-video tasks, providing limited control for fine-grained video content creation. Although adapter-based approaches (e.g., ControlNet) enable additional controls with minimal fine-tuning, they encounter challenges when integrating multiple conditions, including: branch conflicts between independently trained adapters, parameter redundancy leading to increased computational cost, and suboptimal performance compared to full fine-tuning. To address these challenges, we introduce FullDiT, a unified foundation model for video generation that seamlessly integrates multiple conditions via unified full-attention mechanisms. By fusing multi-task conditions into a unified sequence representation and leveraging the long-context learning ability of full self-attention to capture condition dynamics, FullDiT reduces parameter overhead, avoids conditions conflict, and shows scalability and emergent ability. We further introduce FullBench for multi-task video generation evaluation. Experiments demonstrate that FullDiT achieves state-of-the-art results, highlighting the efficacy of full-attention in complex multi-task video generation.
Forward citations
Cited by 13 Pith papers
-
MoZoo:Unleashing Video Diffusion power in animal fur and muscle simulation
MoZoo generates high-fidelity animal videos with fur and muscle dynamics from coarse meshes by extending video diffusion with role-aware RoPE and asymmetric decoupled attention, trained on a new synthetic-to-real dataset.
-
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.
-
ICDepth: Taming Video Diffusion Models for Video Depth Estimation via In-Context Conditioning
ICDepth adapts text-to-video diffusion transformers for video depth estimation via in-context conditioning, achieving SOTA results on benchmarks with 6-13x less training data than prior generative methods.
-
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...
-
SWIFT: Prompt-Adaptive Memory for Efficient Interactive Long Video Generation
SWIFT introduces a semantic injection cache with head-wise updates and an adaptive dynamic window plus segment anchors to achieve efficient multi-prompt long video generation at 22.6 FPS while preserving quality in ca...
-
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.
-
Lighting-grounded Video Generation with Renderer-based Agent Reasoning
LiVER conditions video diffusion models on renderer-derived 3D control signals for disentangled, editable control over object layout, lighting, and camera trajectory.
-
CustomX: Unified Character, Action, and Scene Customization in Video World Models
AniX generates controllable videos of a user-supplied character performing typed actions inside a user-supplied 3D scene by fine-tuning a pre-trained video generator on small locomotion datasets.
-
VideoCanvas: Unified Video Completion from Arbitrary Spatiotemporal Patches via In-Context Conditioning
A single diffusion model with in-context conditioning and fractional RoPE positions completes videos from arbitrary spatio-temporal image patches.
-
UniVideo: Unified Understanding, Generation, and Editing for Videos
UniVideo combines a frozen MLLM and a video DiT to unify video understanding, generation, in-context editing, visual prompting, and zero-shot free-form video edits under one instruction interface.
-
AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization
AnchorWorld proposes a simulation framework that adds exogenous viewpoint supervision for full-body grounding and anchor-view text customization for dynamic world evolution in egocentric settings.
-
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.
-
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...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.