2026-07-22（周三） 收录 10 篇论文：Generative World Renderer at the Speed of Play；Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing；Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers…
Generative world renderer AlayaRenderer receives structured world states exported from physics engines and synthesizes RGB frames. Unlike models that generate frames from text/control-hints prompts, A...
Large-scale visual generators are increasingly capable but costly to train, fine-tune, and deploy. We introduce Mage-Flow, a compact 4B-scale generative stack for efficient text-to-image generation an...
Text-to-image diffusion transformers (DiTs) jointly process text and image tokens, yet their internal computation during denoising remains poorly understood. We introduce a causal interpretability fra...
Unlike conventional video game development, which relies on labor-intensive pipelines for asset production, animation, physics, and programming, video world models generate interactive environments fr...
Asynchronous reinforcement learning improves throughput by decoupling rollout generation from optimization, but staleness is an inevitable byproduct compounded by policy lag, engine delays, and mixtur...
This paper is a practitioner guide to graph-based workflow pathways for long-running, stateful, multi-step generative AI systems in business processes. Rather than treating LangGraph, a low-level orch...
This paper proposes AI Tour Meeting, a group travel planning framework powered by multiple Large Language Model (LLM)-based agents. The agents are instantiated with distinct personas and collaborative...
LLM agent failures are difficult to debug because the step where an error surfaces is often not the one that caused it. Existing observability tools replay execution traces but provide little support ...
We present ABot-World-0, an action-conditioned video world model for real-time, long-horizon closed-loop interaction, supported by a multi-source data infrastructure spanning AAA games, simulation eng...
Efficient teamwork typically combines global coordination with parallel execution, a principle not yet fully reflected in unified Vision-Language Model (VLM)-based document parsers. Existing unified p...