3 papers
cs.AI2025
Semantic-Driven AI Agent Communications: Challenges and Solutions
Kaiwen Yu, Mengying Sun, Zhijin Qin +4
With the rapid growth of intelligent services, communication targets are shifting from humans to artificial intelligent (AI) agents, which require new paradigms to enable real-time…
cs.CV2025
Boosting All-in-One Image Restoration via Self-Improved Privilege Learning
Gang Wu, Junjun Jiang, Kui Jiang +1
Unified image restoration models for diverse and mixed degradations often suffer from unstable optimization dynamics and inter-task conflicts. This paper introduces Self-Improved P…
cs.LG2024
Learning from Students: Applying t-Distributions to Explore Accurate and Efficient Formats for LLMs
Jordan Dotzel, Yuzong Chen, Bahaa Kotb +5
The increasing size of large language models (LLMs) traditionally requires low-precision integer formats to meet strict latency and power demands. Yet recently, alternative formats…