{"work":{"id":"1339e674-d09b-48b4-8e6f-efe55dcab22e","openalex_id":null,"doi":null,"arxiv_id":"2503.20523","raw_key":null,"title":"GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving","authors":null,"authors_text":"Lloyd Russell, Anthony Hu, Lorenzo Bertoni, George Fedoseev, Jamie Shotton, Elahe Arani","year":2025,"venue":"cs.CV","abstract":"Generative models offer a scalable and flexible paradigm for simulating complex environments, yet current approaches fall short in addressing the domain-specific requirements of autonomous driving - such as multi-agent interactions, fine-grained control, and multi-camera consistency. We introduce GAIA-2, Generative AI for Autonomy, a latent diffusion world model that unifies these capabilities within a single generative framework. GAIA-2 supports controllable video generation conditioned on a rich set of structured inputs: ego-vehicle dynamics, agent configurations, environmental factors, and road semantics. It generates high-resolution, spatiotemporally consistent multi-camera videos across geographically diverse driving environments (UK, US, Germany). The model integrates both structured conditioning and external latent embeddings (e.g., from a proprietary driving model) to facilitate flexible and semantically grounded scene synthesis. Through this integration, GAIA-2 enables scalable simulation of both common and rare driving scenarios, advancing the use of generative world models as a core tool in the development of autonomous systems. Videos are available at https://wayve.ai/thinking/gaia-2.","external_url":"https://arxiv.org/abs/2503.20523","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-25T06:35:24.893439+00:00","pith_arxiv_id":"2503.20523","created_at":"2026-05-10T06:26:27.471024+00:00","updated_at":"2026-05-25T06:35:24.893439+00:00","title_quality_ok":true,"display_title":"GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving","render_title":"GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving"},"hub":{"state":{"work_id":"1339e674-d09b-48b4-8e6f-efe55dcab22e","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":30,"external_cited_by_count":null,"distinct_field_count":5,"first_pith_cited_at":"2025-06-11T17:57:09+00:00","last_pith_cited_at":"2026-05-20T11:45:32+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-06-04T05:47:19.334033+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":13}],"polarity_counts":[{"context_polarity":"background","n":13}],"runs":{},"summary":{},"graph":{},"authors":[]}}