Kaipeng Zhang

WorldRover turns long-horizon world exploration into a scalable data-generation problem, providing a treasure trove of richly annotated sequences for training AI models.

Marionette achieves robust long-horizon control in interactive game worlds by explicitly modeling the evolving state while maintaining photorealistic appearance without fidelity loss.

Current AI-generated videos that mislead viewers are also the most challenging for existing detection systems to identify, revealing a critical vulnerability in misinformation defenses.

Evoke achieves state-of-the-art performance in interactive world modeling by externalizing memory and enabling long-horizon supervision, all while maintaining responsiveness and efficiency.

Conditioning signals now match generated content more closely, leading to unprecedented realism in long-horizon video generation.

Explicitly disentangling world dynamics from view rendering allows MAS to achieve unprecedented scalability and consistency in multiplayer simulations.

HelloWorld allows users to engage in seamless social interactions with video characters, achieving superior quality without sacrificing visual aesthetics.

GROVE achieves state-of-the-art performance in memory retrieval for wearable assistants by seamlessly integrating reactive and proactive memory access from continuous video streams.

ShadowDancer enables seamless action transfer across diverse environments by transforming any demonstrated video clip into a reusable action asset without the need for action labels or fine-tuning.

AlayaRenderer-Flash achieves real-time generative rendering at 30 FPS without sacrificing scene fidelity or control.

Surprise Forcing redefines resource allocation in video generation, leading to improved visual quality and consistency without sacrificing streaming speed.

Interactive game worlds can now leverage a scalable data engine that captures 90 hours of gameplay, setting a new standard for state-aware modeling.

OrthoPilot outperformed seasoned orthopaedic experts in diagnostic reasoning, achieving a 10.6% increase in management success for complex musculoskeletal cases.

Proactive assistance can significantly enhance user experience by intelligently deciding when to intervene based on rich contextual understanding rather than waiting for prompts.

AlayaWorld transforms game development by enabling real-time, interactive world generation that adapts to user actions without the need for extensive manual design.

VDMs can tell time is running backward, but still fail at basic causal reasoning, revealing a significant gap between statistical pattern matching and true world model understanding.

MLLMs get personality right half the time for the wrong reasons, revealing a massive "Prejudice Gap" where models fail to ground their judgments in observable behavior.

Stop guessing which interactive video model is best: WorldMark offers the first apples-to-apples comparison across leading models on identical scenes and trajectories.

Training generative inverse renderers on AAA game footage closes the realism gap, enabling superior generalization and controllable generation compared to models trained on existing synthetic datasets.

Forget training on long videos – PackForcing achieves state-of-the-art long-video generation by cleverly compressing the KV-cache into Sink, Mid, and Recent tokens, enabling 24x temporal extrapolation from short-video training.