Hanqi Jiang's Home Page
  • Home
  • Publications
  • Blog

Blog

Research notes on agent memory, trustworthy multimodal AI, and medical AI evaluation.

SYNAPSE: Episodic-Semantic Memory for Long-Horizon LLM Agents

SYNAPSE, accepted to Findings of ACL 2026, turns long-term agent memory from semantic search into spreading activation over an episodic-semantic graph.

Jun 01, 2026

MedVIGIL: Evaluating Trustworthy Medical VLMs Under Broken Visual Evidence

MedVIGIL is a clinician-supervised benchmark for testing whether medical vision-language models fail safely when the visual evidence contract is broken.

May 05, 2026
Last updated: Jun 2026
Copyright © 2025 Hanqi Jiang. All Rights Reserved.