6 papers
When Do Task Vectors Interfere? Mapping the Validity Boundaries of Weight-Space Composition
Chencheng Zhu, Xiaoyang Li, Taotao Cai
Task arithmetic composes skills by adding weight displacements, and merged models are then judged on benchmark suites. We measure when that composition is functionally additive, an…
MAP-Graph: Provenance-Aware Shared Memory for Multi-Agent Workflows
Yiqi Wang, Zihao Yan, Jiaqi Zhang +5
Shared memory helps language-model agents reuse information across long workflows, yet relevant evidence may not be admissible for a particular agent or action. Because restriction…
From Faulty Memories to Corrected Actions: Dependency-Guided Rollback Repair for Memory-Augmented Agents
Caili Yu, Yiqi Wang, Jiaqi Zhang +5
Persistent memory lets language-model agents reuse information across sessions, but it also makes errors durable: a poisoned, stale, or misattributed record can alter reasoning, to…
MemTX: Transactional Belief Commit for Stateful Agent Memory
Xiaoyang Li, Yiqi Wang, Haohui Lu +5
LLM agents increasingly coordinate through persistent shared memory: one agent's write becomes another agent's premise, and eventually a tool call with real side effects. Current a…
Who Owns This Sample: Cross-Client Membership Inference Attack in Federated Graph Neural Networks
Kunhao Li, Di Wu, Jun Bai +7
Graph-structured data is prevalent in many real-world applications, including social networks, financial systems, and molecular biology. Graph Neural Networks (GNNs) have become th…
Deep Learning Model Inversion Attacks and Defenses: A Comprehensive Survey
Wencheng Yang, Song Wang, Di Wu +7
The rapid adoption of deep learning in sensitive domains has brought tremendous benefits. However, this widespread adoption has also given rise to serious vulnerabilities, particul…