10 papers
OBCache: Optimal Brain KV Cache Pruning for Efficient Long-Context LLM Inference
Yuzhe Gu, Xiyu Liang, Jiaojiao Zhao +1
Large language models (LLMs) with extended context windows enable powerful applications but impose significant memory overhead, as caching all key-value (KV) states scales linearly…
A Kinetic Energy Perspective of Flow Matching
Ziyun Li, Huancheng Hu, Soon Hoe Lim +6
Flow-based generative models can be viewed through a physics lens: sampling transports a particle from noise to data by integrating a learned velocity field, and each sample corres…
From Local to Global: Revisiting Structured Pruning Paradigms for Large Language Models
Ziyan Wang, Enmao Diao, Qi Le +6
Structured pruning is a practical approach to deploying large language models (LLMs) efficiently, as it yields compact, hardware-friendly architectures. However, the dominant local…
FedOBP: Federated Optimal Brain Personalization through Cloud-Edge Element-wise Decoupling
Xingyan Chen, Tian Du, Changqiao Xu +4
Federated Learning (FL) faces challenges from client data heterogeneity and resource-constrained mobile devices, which can degrade model accuracy. Personalized Federated Learning (…
RPS: Information Elicitation with Reinforcement Prompt Selection
Tao Wang, Jingyao Lu, Xibo Wang +5
Large language models (LLMs) have shown remarkable capabilities in dialogue generation and reasoning, yet their effectiveness in eliciting user-known but concealed information in o…
Graph Tokenization for Bridging Graphs and Transformers
Zeyuan Guo, Enmao Diao, Cheng Yang +1
The success of large pretrained Transformers is closely tied to tokenizers, which convert raw input into discrete symbols. Extending these models to graph-structured data remains a…