Xi-Ping Hu

DepressionAgent: Reading, Listening, Seeing, and Deliberating Multimodal Evidence for Depression Risk Assessment

Multimodal depression risk assessment requires jointly interpreting textual, acoustic, and visual cues that are often subtle, non-specific, context-dependent, and potentially inconsistent across modalities. Existing multimodal approaches predominantly learn latent representations through feature fusion, leaving the evi...

Towards Robust Temporal Action Detection: Benchmark and A Strong Baseline

Enabling Timely Guidance before Skill Retrieval: Retaining Helpful Warm Tips in Agent Context

Reusable skills help LLM-based agents solve complex tasks, but the agent must receive guidance before it commits to an ineffective approach. Existing skill mechanisms often expose only metadata and load full content on demand, leaving useful guidance unavailable until the agent decides to retrieve it. General memory me...

A Nesterov-Accelerated Byzantine-Robust Federated Learning

Byrd-NAFL seamlessly integrates Nesterov's momentum into the federated learning process alongside Byzantine-resilient aggregation rules to achieve fast and safe convergence against gradient corruption.