Goto

Collaborating Authors

 Large Language Model


LLMs Can Evolve Continually on Modality for X-Modal Reasoning Jiazuo Y u

Neural Information Processing Systems

To this end, we employ a pre-trained vision LLM [20] as the interface and propose a novel Adapter-in-Adapter (AnA) framework, allowing efficient extension and alignment for other modalities.






RUST: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Models

Neural Information Processing Systems

To perform systematic evaluations, we set up 32 various tasks, including improvements to existing multimodal tasks, extension of text-only tasks to multimodal scenarios, and novel methods for risk assessment, which focus on models' basic performance with practical significance.


Intruding with Words: Towards Understanding Graph Injection Attacks at the Text Level

Neural Information Processing Systems

Graph Neural Networks (GNNs) excel across various applications but remain vulnerable to adversarial attacks, particularly Graph Injection Attacks (GIAs), which inject malicious nodes into the original graph and pose realistic threats.