Goku provides a 2M-pair dataset for multi-task structural video editing, Goku-Edit model with MLLM and dual-branch design, and Goku-Bench yielding up to 8% gains in instruction following.
hub
Follow-your-creation: Empowering 4d creation through video inpainting
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
hub tools
citation-role summary
other 1
citation-polarity summary
years
2026 13verdicts
UNVERDICTED 13roles
other 1polarities
unclear 1representative citing papers
LD-Pruning applies latent discrepancy to prune tokens and adaptively skip unconditional branches in VAR models for up to 2.35x faster inference with preserved quality.
StreamingEffect enables real-time 720p human-centric video effect generation on one GPU via teacher-student distillation, keyframe control, and a new 130K video dataset.
DEVIS-GRPO applies online policy gradients with an accumulative small-to-large view sampling strategy and multi-level rewards to improve trajectory-controlled extreme view video generation, reporting gains on Kubric-4D, iPhone, and DL3DV datasets.
ST-BiBench reveals a coordination paradox in which MLLMs show strong high-level strategic reasoning yet fail at fine-grained 16-dimensional bimanual action synthesis and multi-stream fusion.
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.
GeoEdit introduces a Lift-Manipulate-Render-Denoise pipeline with dual-branch denoising and variance-homogeneous injection for 3D-consistent object editing in single photos.
LiveEdit distills a bidirectional video foundation model into a unidirectional streaming editor via three-stage training plus mask caching to reach 12.66 FPS with stable edits.
Disco-LoRA proposes disentangling content-style and content-motion via dual-LoRA with statistical regularization to enable multi-concept video customization.
CP4D generates physically consistent 4D scenes via compositional integration of pre-trained 3D models, hybrid simulator-diffusion motion synthesis, and automated scene composition.
EasyVFX decouples VFX generation via frequency-aware Mixture-of-Experts and test-time training to achieve realistic effects with limited resources.
E²PO uses embedding-level perturbations to maintain intra-group variance and discriminative signal in RL-based preference optimization for generative flow models.
Empirical study shows reward model ensembles mitigate biases like brightness and composition in preference data for image inpainting, yielding better performance than prior methods without architecture changes.
citing papers explorer
-
Goku: A Million-Scale Universal Dataset and Benchmark for Instruction-Based Video Editing
Goku provides a 2M-pair dataset for multi-task structural video editing, Goku-Edit model with MLLM and dual-branch design, and Goku-Bench yielding up to 8% gains in instruction following.
-
Where to Refine, When to Stop: Rethinking Redundancy via Latent Discrepancy for Efficient Visual Autoregressive Generation
LD-Pruning applies latent discrepancy to prune tokens and adaptively skip unconditional branches in VAR models for up to 2.35x faster inference with preserved quality.
-
StreamingEffect: Real-Time Human-Centric Video Effect Generation
StreamingEffect enables real-time 720p human-centric video effect generation on one GPU via teacher-student distillation, keyframe control, and a new 130K video dataset.
-
DEVIS-GRPO: Unleashing GRPO on Dynamic Extreme View Synthesis
DEVIS-GRPO applies online policy gradients with an accumulative small-to-large view sampling strategy and multi-level rewards to improve trajectory-controlled extreme view video generation, reporting gains on Kubric-4D, iPhone, and DL3DV datasets.
-
ST-BiBench: Benchmarking Multi-Stream Multimodal Coordination in Bimanual Embodied Tasks for MLLMs
ST-BiBench reveals a coordination paradox in which MLLMs show strong high-level strategic reasoning yet fail at fine-grained 16-dimensional bimanual action synthesis and multi-stream fusion.
-
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.
-
GeoEdit: Geometry-Aware Object Editing via Dual-Branch Denoising
GeoEdit introduces a Lift-Manipulate-Render-Denoise pipeline with dual-branch denoising and variance-homogeneous injection for 3D-consistent object editing in single photos.
-
LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing
LiveEdit distills a bidirectional video foundation model into a unidirectional streaming editor via three-stage training plus mask caching to reach 12.66 FPS with stable edits.
-
Disco-LoRA: Disentangled Composition of Content, Style, and Motion for Multi-concept Video Customization
Disco-LoRA proposes disentangling content-style and content-motion via dual-LoRA with statistical regularization to enable multi-concept video customization.
-
CP4D: Compositional Physics-aware 4D Scene Generation
CP4D generates physically consistent 4D scenes via compositional integration of pre-trained 3D models, hybrid simulator-diffusion motion synthesis, and automated scene composition.
-
EasyVFX: Frequency-Driven Decoupling for Resource-Efficient VFX Generation
EasyVFX decouples VFX generation via frequency-aware Mixture-of-Experts and test-time training to achieve realistic effects with limited resources.
-
Embedding-perturbed Exploration Preference Optimization for Flow Models
E²PO uses embedding-level perturbations to maintain intra-group variance and discriminative signal in RL-based preference optimization for generative flow models.
-
Follow-Your-Preference++: Rethinking Preference Alignment for Image Inpainting
Empirical study shows reward model ensembles mitigate biases like brightness and composition in preference data for image inpainting, yielding better performance than prior methods without architecture changes.