6 papers
The Semantic Lifecycle in Embodied AI: Acquisition, Representation and Storage via Foundation Models
Shuai Chen, Hao Chen, Yuanchen Bei +3
Semantic information in embodied AI is inherently multi-source and multi-stage, making it challenging to fully leverage for achieving stable perception-to-action loops in real-worl…
DaGRPO: Rectifying Gradient Conflict in Reasoning via Distinctiveness-Aware Group Relative Policy Optimization
Xuan Xie, Xuan Wang, Wenjie Wang +2
The evolution of Large Language Models (LLMs) has catalyzed a paradigm shift from superficial instruction following to rigorous long-horizon reasoning. While Group Relative Policy…
Empowering LLMs with Structural Role Inference for Zero-Shot Graph Learning
Heng Zhang, Jing Liu, Jiajun Wu +8
Large Language Models have emerged as a promising approach for graph learning due to their powerful reasoning capabilities. However, existing methods exhibit systematic performance…
ACPO: Adaptive Curriculum Policy Optimization for Aligning Vision-Language Models in Complex Reasoning
Yunhao Wang, Ziting Li, Shuai Chen +6
Aligning large-scale vision-language models (VLMs) for complex reasoning via reinforcement learning is often hampered by the limitations of existing policy optimization algorithms,…
EvoP: Robust LLM Inference via Evolutionary Pruning
Shangyu Wu, Hongchao Du, Ying Xiong +4
Large Language Models (LLMs) have achieved remarkable success in natural language processing tasks, but their massive size and computational demands hinder their deployment in reso…
Retrieval-Augmented Generation by Evidence Retroactivity in LLMs
Liang Xiao, Wen Dai, Shuai Chen +4
Retrieval-augmented generation has gained significant attention due to its ability to integrate relevant external knowledge, enhancing the accuracy and reliability of the LLMs' res…