EgoPlay: Event-Triggered Video Editing for Egocentric Streams
Event-triggered video editing for egocentric streams. Given "when X happens, do Y", EgoPlay edits only what comes after the event.
Sep 15, 2026
ContextFlow: In-Context Flow Matching for Robot Manipulation
In-context flow matching for continuous robot control. +35 pp over ICRT on unseen LIBERO configurations, matching fine-tuned π0 without test-time fine-tuning.
Sep 6, 2026
EasyV2V: A High-quality Instruction-based Video Editing Framework
SOTA video editing framework.
Feb 20, 2026
Diffusion-Based Imaginative Coordination for Bimanual Manipulation
A diffusion model that jointly predicts future frames and actions for bimanual manipulation.
Oct 19, 2025
4D-Bench: Benchmarking Multi-modal Large Language Models for 4D Object Understanding
A benchmark for evaluating multimodal LLMs on 4D object understanding.
Oct 18, 2025
Sora3R: Can Video Diffusion Model Reconstruct 4D Geometry ?
We repurpose video diffusion models to reconstruct 4D geometry (4D pointmaps) from monocular video.
Mar 16, 2025
TrackNeRF: Bundle Adjusting NeRF from Sparse and Noisy Views via Feature Tracks
We introduce global bundle adjustment for NeRFs, significantly improving the quality of novel view synthesis from sparse views with noisy poses or even without poses.
Sep 1, 2024
Vivid-ZOO: Multi-View Video Generation with Diffusion Model
We propose multiview video diffusion models that generate high-quality multi-view videos for dynamic objects from text.
Jun 14, 2024
GES: Generalized Exponential Splatting for Efficient Radiance Field Rendering
An improvement of 3D Gaussian Splatting.
Jun 1, 2024
Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors
We propose to use both 2D and 3D diffusion models through SDS optimization to generate high-quality, textured 3D meshes from a single image in the wild.
Mar 14, 2024