Xinpeng Li

Hybrid-thinking LLMs can be dramatically improved by simply separating the feed-forward pathways for reasoning and non-reasoning modes, leading to less leakage and better accuracy.

Asymmetric encoders, trained with a novel two-stage approach, can beat symmetric LLM-based models in Chinese medical text retrieval while maintaining low latency.

Quantum cloud providers can now efficiently schedule parallel jobs on modular QPUs, optimizing qubit mapping and teleportation for fair resource allocation.

Agent evaluation is bottlenecked by environment interaction overhead, but ACE-Bench slashes this by using static JSON files, enabling fast and reproducible training-time validation.