3 papers
cs.AI2026
SKILL-DISCO: Distilling and Compiling Agent Traces into Reusable Procedural Skills
Zhongxin Guo, Danrui Qi, Hanwen Gu +2
Agents often repeatedly solve similar task instances from scratch, leading to unnecessary reasoning cost and long execution traces. Prior work has explored workflow reuse and execu…
cs.AR2026
LUMINA: LLM-Guided GPU Architecture Exploration via Bottleneck Analysis
Tao Zhang, Rui Ma, Shuotao Xu +2
GPU design space exploration (DSE) for modern AI workloads, such as Large-Language Model (LLM) inference, is challenging because of GPUs' vast, multi-modal design spaces, high simu…
cs.AR2025
TENET: An Efficient Sparsity-Aware LUT-Centric Architecture for Ternary LLM Inference On Edge
Zhirui Huang, Rui Ma, Shijie Cao +5
Ternary quantization has emerged as a powerful technique for reducing both computational and memory footprint of large language models (LLM), enabling efficient real-time inference…