Rocket - Think it. Type it. Launch it.
Mini toolsPapers
Filter by company
-
Process-of-Thought Reasoning for Videos
-
gQIR: Generative Quanta Image Reconstruction
-
Tuning-free Visual Effect Transfer across Videos
-
SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices
-
ArtifactLens: Hundreds of Labels Are Enough for Artifact Detection with VLMs
-
OmniView: An All-Seeing Diffusion Model for 3D and 4D View Synthesis
-
S2DiT: Sandwich Diffusion Transformer for Mobile Streaming Video Generation
-
RigMo: Unifying Rig and Motion Learning for Generative Animation
-
Sprint: Sparse-Dense Residual Fusion for Efficient Diffusion Transformers
-
AHA! Animating Human Avatars in Diverse Scenes with Gaussian Splatting
-
Animated 3DGS Avatars in Diverse Scenes with Consistent Lighting and Shadows
-
FlashVLM: Text-Guided Visual Token Selection for Large Multimodal Models
-
EasyV2V: A High-quality Instruction-based Video Editing Framework
-
TalkVerse: Democratizing Minute-Long Audio-Driven Video Generation
-
Omni-Attribute: Open-vocabulary Attribute Encoder for Visual Concept Personalization
-
HybridToken-VLM: Hybrid Token Compression for Vision-Language Models
-
MM-CoT:A Benchmark for Probing Visual Chain-of-Thought Reasoning in Multimodal Models
-
EgoEdit: Dataset, Real-Time Streaming Model, and Benchmark for Egocentric Video Editing
-
SMP: Reusable Score-Matching Motion Priors for Physics-Based Character Control
-
Canvas-to-Image: Compositional Image Generation with Multimodal Controls
-
LayerComposer: Multi-Human Personalized Generation via Layered Canvas
-
AlphaFlow: Understanding and Improving MeanFlow Models
-
GiGL: Large-Scale Graph Neural Networks at Snapchat
-
InstantRestore: Single-Step Personalized Face Restoration with Shared-Image Attention
-
SF-V: Single Forward Video Generation Model
-
General-Purpose User Modeling with Behavioral Logs
-
Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis
-
Knowledge Diffusion for Distillation
-
SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds
