AI Paper Atlas

Research map / Video / Video-language understanding

EgoEdit: Dataset, Real-Time Streaming Model, and Benchmark for Egocentric Video Editing

Runjia Li, Moayed Haji-Ali, Ashkan Mirzaei, Chaoyang Wang, Arpit Sahni, Ivan Skorokhodov, Aliaksandr Siarohin, Tomas Jakab, Junlin Han, Sergey Tulyakov, Philip Torr, Willi Menapace

CVPR 2026 · Video › Video-language understanding · approach: Egocentric video understanding · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add EgoEditData (0% to 25%) (ablation)EgoEdit · EgoEditBench (10k-iteration checkpoint)VLM score: 4.87 -> 7.12Improved
increase EgoEditData from 25% to 75% (ablation)EgoEdit · EgoEditBench (10k-iteration checkpoint)VLM score: 7.12 -> 7.52Improved
increase EgoEditData from 75% to 100% (ablation)EgoEdit · EgoEditBench (10k-iteration checkpoint)VLM score: 7.52 -> 7.85Improved
add 4-step DMD distillation (ablation)EgoEdit · EgoEditBenchVLM score: 7.76 -> 7.31Hurt
add 4-step DMD distillation (ablation)EgoEdit · EgoEditBenchfirst chunk latency (ms): 13432 -> 6925Improved
add Self Forcing after DMD (ablation)EgoEdit · EgoEditBenchVLM score: 7.31 -> 7.71Improved
add Self Forcing after DMD (ablation)EgoEdit · EgoEditBenchfirst chunk latency (ms): 6925 -> 855Improved
distill with DMD plus Self Forcing vs no distillation (ablation)EgoEdit · EgoEditBenchVLM score: 7.76 -> 7.71No clear effect
use EgoEdit-RT instead of StreamDiffusionV2streaming editor · EgoEditBenchVLM score: 2.55 -> 7.71Improved
use EgoEdit instead of Lucy Editinstruction-guided editor · EgoEditBenchVLM score: 5.44 -> 7.76Improved
shift from general editing to egocentric tasksEgoEdit · EgoEditBench vs EditVerseBenchVLM score: 8.00 -> 7.76Hurt
shift from general editing to egocentric tasksLucy Edit · EgoEditBench vs EditVerseBenchVLM score: 6.27 -> 5.44Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy