activity
20212026
most citedParameterized Knowledge Transfer for Personalized Federated Learning

25 citations · 37 across the 5 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2025

Think How to Think: Mitigating Overthinking with Autonomous Difficulty Cognition in Large Reasoning Models

Yongjiang Liu, Haoxi Li, Xiaosong Ma +2

Recent Large Reasoning Models (LRMs) excel at complex reasoning tasks but often suffer from overthinking, generating overly long and redundant reasoning trajectories. To explore it…