EgoXperience learns world-grounded egocentric video reconstruction
EgoX cuts camera, hand, and depth errors by 68.9%, 65.6%, and 42.9% versus the strongest baselines.
Stories per day · 30 days
2 RSS
Relatedworld-models33d-reconstruction1computer-vision1dao1generative-simulation1interactive-agents1jing1language-conditioning1robot-navigation1sim-to-real1slam1
13 stories, newest first · one card per story
Stories tagged #egocentric-video
ScaleNav pretrains language-conditioned robot navigation on internet video
Authors report 86.5% success on adapted Short-Horizon OVON and 94.9% on HabitatGS-LN, then tested a real quadruped.
Generative World Simulation with DAO and JING
DAO and JING couple a persistent shared world state with continuous first-person audiovisual generation.
λ_0 humanoid model uses 500 hours of human loco-manipulation data
Zero-shot transfer to Unitree G1 reached 90.0% on SIMPLE and 62.5% on real loco-manipulation tasks.
Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction
ME-World generates synchronized first-person streams for multiple agents using fine-grained shared-world actions.
Never Look Back: Understanding Persistence in 3D Object Memory from Egocentric Videos
Ledger, a persistent 3D object memory, lifts HD-EPIC accuracy from 29.7% to 42.6% on egocentric video.
World Action Learning via Interaction-Centric Spectral Latent Guidance
WING transfers interaction knowledge from egocentric human video to robot policies via spectral latent guidance.
MemLife: Curating and Reasoning over Long-Term Egocentric Video Memories
MemLife builds entity-grounded text memories from long egocentric video and retrieves them without rewatching clips.
EgoTools: Towards Tool-Centric Reasoning in Real-World Egocentric Videos
EgoTools adds 100 hours of egocentric tool-use video and a 1,000-question benchmark where current VLMs still struggle.
InfiniHand: Streaming World-Space Hand Motion Estimation from Egocentric Video
InfiniHand jointly estimates MANO parameters, camera trajectories, and hand locations from uncalibrated egocentric video.
Ambient @ EgoProactive 2026 : Proactive Egocentric Assistance with Visually Grounded Supervision
ECCV 2026 challenge winner reformulates egocentric intervention timing as single-token classification, boosting macro-F1 by 0.249 over free-form generation.
Ambient @ EgoLongQA 2026: Distilling Long-Video perception into a Sub-2B Model
Ambient team wins EgoLongQA 2026 sub-2B division by distilling an agentic long-video perception pipeline into a 2B vision-language model.
TempCloze: Can Video-LLMs Identify the Missing Middle?
TempCloze benchmark tests Video-LLMs' temporal reasoning with 1,521 videos, finding temporal alignment is the primary failure mode across 31 models.