ALT AI video co-director multi-agent pipeline. Top: The Orchestrator Agent utilizes MAB to navigate a factored creative action space. Bottom: The Pre-Production Agent synthesizes a creative brief, storyline, and visual assets to establish a consistent storyboard, which the Production Agent translates into synchronized keyframes, video clips, and audio. An MLLM Judge evaluates the final video to generate a factored reward signal which is propagated back to the MAB to iteratively refine the creative configuration over optimization loops.

ALT Life of a shipment: from the manufacturer in Groningen (Netherlands) to the customer in Versailles (France), a poffert makes most of its journey in the middle-mile network of the freight forwarder.

ALT Overview of the Retrieve-for-Train framework. Step 1: trains a fan-out language model (FOLM) using RL to produce property-aligned sub-queries. Step 2: uses the trained FOLM to synthesize supervision data. Step 3: trains a diffusion-based fan-out retriever that samples content embeddings directly from query embeddings.

ALT While prior art generates tool-use datasets by searching solutions of user queries with low pass rate, ToolGrad generates successful tool-use chains before generating prompts, yielding high pass rate.