paper-with-me

Papers

GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving

2025-03-26 · Lloyd Russell, Anthony Hu, Lorenzo Bertoni, George Fedoseev, Jamie Shotton, Elahe Arani, Gianluca Corrado

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.

📄 PDF Abstract BibTeX arXiv:2503.20523

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingVideo Generation

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

GAIA-1: A Generative World Model for Autonomous Driving

2023-09-29 · Anthony Hu, Lloyd Russell, Hudson Yeo, Zak Murez 외

Autonomous driving promises transformative improvements to transportation, but building systems capable of safely navigating the unstructured complexity of real-world scenarios remains challenging. A critical problem lie…

Autonomous Driving

GAIA: Zero-shot Talking Avatar Generation

2023-11-26 · Tianyu He, Junliang Guo, Runyi Yu, Yuchi Wang 외

Zero-shot talking avatar generation aims at synthesizing natural talking videos from speech and a single portrait image. Previous methods have relied on domain-specific heuristics such as warping-based motion representat…

Diversity

GAIA-v2-LILT: Multilingual Adaptation of Agent Benchmark beyond Translation

2026-04-27 · Yunsu Kim, Kaden Uhlig, Joern Wuebker arxiv

Agent benchmarks remain largely English-centric, while their multilingual versions are often built with machine translation (MT) and limited post-editing. We argue that, for agentic tasks, this minimal workflow can easil…

Machine Translation

PhysGaia: A Physics-Aware Dataset of Multi-Body Interactions for Dynamic Novel View Synthesis

2025-06-03 · Mijeong Kim, Gunhee Kim, Jungyoon Choi, Wonjae Roh 외

We introduce PhysGaia, a novel physics-aware dataset specifically designed for Dynamic Novel View Synthesis (DyNVS), encompassing both structured objects and unstructured physical phenomena. Unlike existing datasets that…

Novel View SynthesisScene Understanding

GAIA: Categorical Foundations of Generative AI

2024-02-28 · Sridhar Mahadevan

In this paper, we propose GAIA, a generative AI architecture based on category theory. GAIA is based on a hierarchical model where modules are organized as a simplicial complex. Each simplicial complex updates its intern…