Chao Yang

FlowTracer reveals that optimizing token-level rewards based on attention-induced information flow can dramatically enhance reasoning performance in LLMs.

Resource-constrained edge devices can achieve Pareto-optimal trade-offs between inference accuracy, latency, and energy consumption in federated learning by using a constrained multi-objective reinforcement learning approach.

By explicitly verifying the visual existence of spoken references before segmentation, APRVOS substantially improves robustness in noisy audio-conditioned Ref-VOS, outperforming standard pipelines.

LLM-based multi-agent systems are riddled with 20 distinct risk types, from single-agent vulnerabilities to system-level emergent hazards, demanding a unified safety evaluation and monitoring framework.

By explicitly optimizing for both reasoning structure and chemical consistency, Logos offers a pathway to reliable and interpretable AI systems for molecular science, outperforming larger models with a fraction of the parameters.

Adapt your traffic forecasting models to real-world shifts in demand with FORESEE, a parameter-free online learning method that slashes computational costs while boosting accuracy and robustness.

Ditch the min-max: Fuz-RL offers a fuzzy-measure guided approach to safe RL that achieves distributional robustness without complex optimization.