LoGo: local-global rewards fix 3D inconsistency in camera-controlled video models
georgiagkioxari · x · 2026-11-20
Caltech PhD student Ziqi Ma will present LoGo at Cohere Labs' open science community (Nov 24, 8am PST), tackling 3D inconsistency in camera-controlled video models. Existing post-training assigns a single scalar reward per generation, poorly suited to long horizons. LoGo blends a spatially localized reward (fine-grained credit assignment, substantially improving 3D consistency) with a global reward (preserving camera following and quality). Across three base models it shows clear gains on DL3DV and a new long-horizon benchmark, TrajectoryBench, reducing object shifts, artifacts, and scene drift. Ma's research focuses on video-based world models capturing physical priors; she has interned at World Labs and Meta SuperIntelligence Labs.
More from Multimodal
- Saudi Arabia's HUMAIN launches Arabic-first voice AI platform HUMAIN Voice — HUMAIN · 2026-11-20
- Google ships Genie 4 on Gemini API and AI Studio with live WASD steering — _philschmid · 2026-11-20
- Salesforce releases BLIP-Live: SOTA proactive streaming video understanding with PAUC-F metric — Salesforce · 2026-11-20
- Cockroaches play a game of Mafia in absurd AI-generated video demo — ayushtweetshere · 2026-11-20
- Ideogram 4.6 launches with precise editing and native 4K output — lyraxana · 2026-11-20
- Eno Reyes releases 'the builder (2026)', a short film made with no crew — sonofalli · 2026-11-20