Yiming Li

The paper proposes TimeGuard, a novel channel-wise pool training defense, to significantly improve the robustness of time series forecasting against backdoor attacks by addressing signal dilution and loss degeneration.

The paper proposes BiCoT, a novel watermarking framework that embeds ownership signals into the internal structure of Chain-of-Thought reasoning traces, achieving robust detection without compromising the model's reasoning fidelity.

The paper proposes Cert-LAS, a novel certified method for verifying model ownership in text-to-image diffusion models, which is robust against malicious signal removal attacks.

The paper argues that current embodied planning benchmarks prioritize superficial language prediction over true physical reasoning, introducing new benchmarks and a large-scale dataset to demonstrate that physically grounded causal reasoning is necessary for reliable autonomous agents.

The paper argues that current embodied planning benchmarks prioritize superficial language prediction over true physical reasoning, introducing new benchmarks and a large-scale dataset to demonstrate that physically grounded causal reasoning is necessary for reliable autonomous agents.

The paper addresses the modality gap between text and speech in spoken dialogue models by redesigning speech tokens to increase semantic density and efficiency.

This paper introduces a stakeholder-centric benchmark to evaluate the vulnerabilities of large language models in web agent systems.

The authors demonstrate dual-line coherent detection using an optical frequency comb local oscillator.

xDSM is a full-space, elastic DSM system built over CXL that transparently scales unmodified multithreaded applications by employing an OS-runtime co-design, dynamic data placement policy, and spatial locality-aware elasticity.