8 papers
Thousand-GPU Large-Scale Training and Optimization Recipe for AI-Native Cloud Embodied Intelligence Infrastructure
Yongjian Guo, Yunxuan Ma, Haoran Sun +22
Embodied intelligence is a key step towards Artificial General Intelligence (AGI), yet its development faces multiple challenges including data, frameworks, infrastructure, and eva…
SD-PSFNet: Sequential and Dynamic Point Spread Function Network for Image Deraining
Jiayu Wang, Haoyu Bian, Haoran Sun +1
Image deraining is crucial for vision applications but is challenged by the complex multi-scale physics of rain and its coupling with scenes. To address this challenge, a novel app…
Preference-Aware Memory Update for Long-Term LLM Agents
Haoran Sun, Zekun Zhang, Shaoning Zeng
One of the key factors influencing the reasoning capabilities of LLM-based agents is their ability to leverage long-term memory. Integrating long-term memory mechanisms allows agen…
Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents
Haoran Sun, Shaoning Zeng
Long-term memory is one of the key factors influencing the reasoning capabilities of Large Language Model Agents (LLM Agents). Incorporating a memory mechanism that effectively int…
An Uncertainty-Driven Adaptive Self-Alignment Framework for Large Language Models
Haoran Sun, Zekun Zhang, Shaoning Zeng
Large Language Models (LLMs) have demonstrated remarkable progress in instruction following and general-purpose reasoning. However, achieving high-quality alignment with human inte…
A Novel Self-Evolution Framework for Large Language Models
Haoran Sun, Zekun Zhang, Shaoning Zeng
The capabilities of Large Language Models (LLMs) are limited to some extent by pre-training, so some researchers optimize LLMs through post-training. Existing post-training strateg…