Siyuan Qi

DynaTree introduces a two-stage framework that pre-constructs a reusable retrieval tree offline using coordinated agents, allowing for efficient, structure-aware, and highly effective time-sensitive news retrieval online.

This paper proposes HDR (Hierarchical Denoising for Visual Reasoning), a framework that integrates hierarchical latents into causal video generation for multi-step reasoning, enabling coarse-to-fine reasoning and reducing temporal attention costs.