Jian Liu

The paper demonstrates that on public blockchains, the ability to dictate transaction order (ordering power) is the true source of sanctioning power, as block producers can extract value (SE-MEV) by prioritizing transactions that evade sanctions.

FedSpy-LLM introduces a scalable and generalizable data reconstruction attack that can extract private training data from shared gradients of large language models, even when using Parameter-Efficient Fine-Tuning (PEFT) methods.

The paper introduces EgoBench, the first interactive multimodal benchmark designed to jointly evaluate advanced AI agents' capabilities in visual perception, multi-hop reasoning, and dynamic tool usage in real-world, egocentric scenarios.

The paper proposes HetMedAgent, a multi-agent framework, demonstrating that combining generalist LLMs with domain-specific specialist models significantly improves medical AI performance by enabling structured collaboration.

The paper proposes a novel symmetry-aware, category-level method for 9D object pose estimation that accurately estimates translation and size first, followed by rotation, achieving state-of-the-art results on diverse objects.