TaskHC: Function-Structured Persistent States with Operation-Dependent Access

Classification and localization require different visual evidence, yet standard detection transformers accumulate and integrate information for both tasks in a single shared state per query. We introduce TaskHC, which extends Hyper-Connections by organizing persistent residual streams into functional groups. Task-specific working states are reconstructed from designated groups, and task updates are written back to them; shared modules reconstruct a joint working state from the full stream bank and mix residual information across groups. Architectural ablations show that group-specific reconstruction and writeback improve detection over access to the full stream bank with the task-specific modules held fixed, and that shared modules benefit from cross-group mixing. Sampling analyses and frozen-state probes reveal specialization in evidence acquisition and task-information accessibility. On COCO, TaskHC improves matched DEIM–D-FINE and DEIM–RT-DETRv2 baselines. For DEIM–D-FINE-L, AP increases from 54.45 to 54.68 with 0.53 ms additional latency on an NVIDIA T4 using TensorRT FP16.