Julian McAuley

Leveraging dialogue as a conditioning signal significantly enhances video-to-music generation, outperforming existing models with a novel dataset that ensures reproducibility.

Mechanist uncovers a surprising safety risk where unsafe traits can transfer across modalities, challenging assumptions about training data safety.

Agentic Commerce World reveals that process-level evidence is crucial for accurately evaluating AI agents in dynamic market environments, challenging traditional reliance on final outcomes alone.

LLMs can now generate more relevant and factual movie recommendations by dynamically bridging retrieval and generation with a novel reinforcement learning approach.

Forget end-to-end image generation – this work shows that explicitly interleaving textual reasoning with visual refinement, guided by dense supervision, yields more controllable and interpretable image synthesis.