Hao Zhu

The paper introduces PIDP-Attack, a novel compound adversarial attack that combines prompt injection with database poisoning to manipulate Retrieval-Augmented Generation (RAG) systems against arbitrary queries without prior knowledge.

Opal is a private memory system for personal AI that maintains high retrieval accuracy and throughput while ensuring data privacy by confining all data-dependent reasoning to a trusted hardware enclave.

The paper argues that web agents should abandon the reactive ReAct paradigm in favor of a plan-then-execute approach, which requires developing typed, task-level APIs to properly structure web interactions.

ContraFix is an agentic framework that improves automated vulnerability repair by using differential runtime evidence to pinpoint the root cause of bugs, achieving state-of-the-art performance on major benchmarks.

The paper introduces PMC-InterCPT, a refined biomedical interleaved corpus that enhances multimodal continued pretraining by integrating figure-referencing body text alongside captions, leading to improved medical and general multimodal model performance.

This paper introduces AutoMem, a framework that automates memory management as a trainable skill for large language models, improving performance up to 2x-4x on long-horizon tasks.

This paper proposes a Kalman filter-assisted data-predictive SAR ADC to reduce switching energy and latency in ultra-low-power IoT devices.

The paper derives an explicit representation for the Euclidean dual of Hyperderivative Reed-Solomon codes and studies reverse self-dual HRS codes.