3 papers
cs.CL2026
TF-Engram: A Train-Free Engram with SSD-Backed Memory for Large Language Models
Yutang Ma, Kecheng Huang, Xikun Jiang +1
Large Language Models (LLMs) store factual knowledge and domain-specific patterns implicitly in dense Transformer parameters, making knowledge expansion costly through pretraining,…
cs.NE2026
Kernel Foundry: A Diagnosis-driven Evolutionary Kernel Optimizer with Multi-Experts
Zixuan Huang, Da Chen, Kecheng Huang +5
Generating high-performance GPU kernels remains challenging due to the need for both correctness and hardware-aware optimization. While large language models (LLMs) show promise in…
cs.LG2025
Attention-Aware GNN-based Input Defense against Multi-Turn LLM Jailbreak
Zixuan Huang, Kecheng Huang, Lihao Yin +4
Large Language Models (LLMs) have gained significant traction in various applications, yet their capabilities present risks for both constructive and malicious exploitation. Despit…