Yang Tang

Delayed feedback in reinforcement learning can be effectively managed by modeling discrepancies with diffusion techniques, leading to improved policy performance in challenging environments.

LazyMCoT achieves training-free visual grounding that rivals traditional methods while cutting inference time, redefining efficiency in multimodal reasoning.

Projector Drift reveals a hidden vulnerability in omni-modal systems that can significantly impair audio retrieval, but a simple fine-tuning strategy can effectively address it.

Foundation models are poised to revolutionize multi-agent systems by enabling semantic-level reasoning and flexible coordination that surpasses the limitations of classical approaches.

Unlock the power of MLLMs for structured data like human skeletons with a differentiable rendering approach that allows end-to-end training.