Code World Model 2.0: Towards Infinite Controllable Video Generation
11 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 9 tương tác đã đo · Nguồn crawl
Chi tiết nguồn
Bài báo mô tả cách các “visual proxies” tách việc mô phỏng trạng thái thế giới khỏi sinh video hiện thực, cung cấp một giao diện điều khiển cho tạo clip ngoại tuyến và streaming tương tác thời gian thực. Họ nêu hai thách thức: các proxy thay đổi theo mức độ tương tác, và suy luận streaming cần chạy trong vài bước nhân quả mà không tích lũy trôi do lịch sử tự sinh.
Visual proxies decouple explicit world-state simulation from photorealistic video synthesis, offering a controllable interface for both offline clip creation and real-time interactive streaming. Yet a practical renderer must address two challenges. Upstream proxies vary from coarse layouts to fine articulated geometry depending on the interaction, and streaming inference must operate in a few causal steps without accumulating drift across self-generated history. We present Invoker-Render, pairing a bidirectional creation model with a causal four-step streaming model under a shared conditioning interface over structural proxies, an appearance reference, and language. Trained on an aligned approximately 200-hour multi-granularity corpus, Invoker-Render honors fine geometric constraints when supplied while synthesizing plausible local motion under coarse proxies, enabling runtime selection of input detail. To bridge bidirectional creation and real-time streaming without compounding step compression and rollout drift, we introduce Progressive Forcing (ProForcing). ProForcing first trains a causal predictor and distills it into a four-step renderer using histories derived from training videos. Training then shifts to continuous self-generated rollouts. A pipelined serving stack supports efficient streaming inference. Experiments show versatile control across proxy families, granularities, and camera paths, consistent gains over recent streaming baselines, and stable 30-minute racing rollouts that preserve scene and subject appearance.
We present Invoker-Render, pairing a bidirectional creation model with a causal four-step streaming model under a shared conditioning interface over structural proxies, an appearance reference, and language.
We present Invoker-Render, pairing a bidirectional creation model with a causal four-step streaming model under a shared conditioning interface over structural proxies, an appearance reference, and language.
To bridge bidirectional creation and real-time streaming without compounding step compression and rollout drift, we introduce Progressive Forcing (ProForcing).
Experiments show versatile control across proxy families, granularities, and camera paths, consistent gains over recent streaming baselines, and stable 30-minute racing rollouts that preserve scene and subject appearance.
- Code World Model 2.0: Towards Infinite Controllable Video Generation Hugging Face Papers · 17 thg 11, 2026