Publications

(2026). Nabla: Adaptive Multi-Domain DVFS for Energy-Efficient LLM Inference on Edge SoCs. Under Review
(2026). Loom: Criticality Inference via Efficient Causal Dependency Graph Mining. Under Review
(2026). Unleash All Cores: Asymmetry-aware Scalable DNN Inference on Mobile CPUs. In OSDI CCF-A Cite Source Document
(2026). Trident: Identifying, Constraining and Multi-Domain Governing for Resource Management on Mobile Devices. In IEEE TMC CCF-A Cite
(2026). QDiTx: Arbitrary Bit-Width Quantization Framework for Diffusion Transformer. In IEEE TCAD CCF-A
(2024). QoS-Aware Power Management via Scheduling and Governing Co-Optimization on Mobile Devices. In IEEE TMC CCF-A PDF Cite
(2024). Incendio: Priority-Based Scheduling for Alleviating Cold Start in Serverless Computing. In IEEE TC CCF-A