PaperFlume PrivacyTerms Library
Overview · 0:54

NanoFLUX: Distillation-Driven Compression of Large Text-to-Image Generation Models for Mobile Devices

Watch the full walkthrough Get the deck
Overview · 0:47

DirectEdit: Step-Level Accurate Inversion for Flow-Based Image Editing

Watch the full walkthrough Get the deck
Overview · 0:52

Concept-Guided Tokenization: Closing the Gap Between Reconstruction and Generation

Watch the full walkthrough Get the deck
Overview · 0:49

DiffCrossGait: Trajectory-Level Alignment for 2D-3D Cross-Modal Gait Recognition via Latent Diffusion

Watch the full walkthrough Get the deck
Overview · 0:52

HALO: Hybrid Auto-encoded Locomotion with Learned Latent Dynamics, Poincaré Maps, and Regions of Attraction

Watch the full walkthrough Get the deck
Overview · 0:52

GaussTrace: Provenance Analysis of 3D Gaussian Splatting Models with Evidence-based LLM Reasoning

Watch the full walkthrough Get the deck
Overview · 0:49

Revisiting Photometric Ambiguity for Accurate Gaussian-Splatting Surface Reconstruction

Watch the full walkthrough Get the deck
Overview · 0:50

Scalable and Differentiable Point-Cloud Registration Using Maximum Mean Discrepancy

Watch the full walkthrough Get the deck
Overview · 0:45

RGGT: A Generative-Prior-Guided Transformer for Unified Rigid and Non-Rigid Point Cloud Registration

Watch the full walkthrough Get the deck
Overview · 0:43

PVDepth: Panoramic Video Depth Estimation via Geometry-Aware Spatiotemporal Adaptation

Watch the full walkthrough Get the deck
Overview · 0:51

PointCHR: Point Cloud Analysis via Curvature-Aware Hyperbolic Rectification

Watch the full walkthrough Get the deck
Overview · 0:54

PolarDepth: Monocular Transparent Object Depth from Polar-Physics Priors

Watch the full walkthrough Get the deck
Overview · 0:54

SMD: Multi-view Safety-Critical Driving Video Generation in the Real-world Domain

Watch the full walkthrough Get the deck
Overview · 0:46

DynaTok: Token-Based 4D Reconstruction from Partial Point Clouds

Watch the full walkthrough Get the deck
Overview · 0:55

VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization

Watch the full walkthrough Get the deck
Overview · 0:48

Learned Incremental Nonlinear Dynamic Inversion for Quadrotors with and without Slung Payloads

Watch the full walkthrough Get the deck
Overview · 0:47

MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance

Watch the full walkthrough Get the deck
Overview · 0:55

CG-MLLM: Captioning and Generating 3D Content via Multi-modal Large Language Models

Watch the full walkthrough Get the deck
Overview · 0:47

Wheeled Lab: Modern Sim2Real for Low-cost, Open-source Wheeled Robotics

Watch the full walkthrough Get the deck
Overview · 0:52

3DGS-HPC: Distractor-free 3D Gaussian Splatting with Hybrid Patch-wise Classification

Watch the full walkthrough Get the deck
End of page 10

There are more.

You have seen 20 short cuts. The library has more papers than fit in one feed.

Next 20 Browse the library instead
1 / 20