[ACL Findings 2026] Official Implementation of "RePrompT: Recurrent Prompt Tuning for Integrating Structured EHR Encoders with Large Language Models"

Parameter-efficient multitask learning via soft context prompt tuning (SoftCPT) and visual prompt tuning (VPT). Adapts vision-language models for simultaneous age, gender, and emotion recognition from facial images.

We optimize a compact latent state (frozen weights) to force failed multi-hop chains to output the missing answer D. 5 pre-registered controls show it simply injects D: carries it without the code-fact, leaves intermediates invisible, inert to hop corruption, and doesn’t transfer. No latent composition at 3B (Llama-3.2-3B, Qwen2.5-3B).