Publications

[Google Scholar]

2025

  1. Unifying Vision-Language Latents for Zero-label Image Caption Enhancement, NeurIPS UniReps, PMLR
  2. APCE: Adaptive Progressive Context Expansion for Long Context Processing, NeurIPS ML For Systems
  3. 3-Model Speculative Decoding, NeurIPS SPIGM
  4. Performance Implications of Multi-Chiplet Neural Processing Units on Autonomous Driving Perception, DATE
  5. DisCovHAR: Contrastive Attention for Human Activity Recognition Under Distribution Shifts, IEEE IoTJ

2024

  1. SCAR: Scheduling Multi-Model AI Workloads on Heterogeneous Multi-Chiplet Module Accelerators, MICRO

2023

  1. Map-and-Conquer: Energy-Efficient Mapping of Dynamic Neural Nets onto Heterogeneous MPSoCs, DAC
  2. SEO: Safety-Aware Energy Optimization Framework for Multi-Sensor Neural Controllers at the Edge, DAC
  3. EnergyShield: Provably-Safe Offloading of Neural Network Controllers for Energy Efficiency, ICCPS
  4. HADAS: Hardware-Aware Dynamic Neural Architecture Search for Edge Performance Scaling, DATE
  5. MaGNAS: A Mapping-Aware Graph Neural Architecture Search Framework for Heterogeneous MPSoC Deployment, ACM TECS
  6. PrivyNAS: Privacy-Aware Neural Architecture Search for Split Computing in Edge–Cloud Systems, IEEE IoTJ
  7. Inter-layer Scheduling Space Exploration for Multi-Model Inference on Heterogeneous Chiplets, arXiv

2022

  1. Romanus: Robust Task Offloading in Modular Multi-Sensor Autonomous Driving Systems, ICCAD
  2. Template Matching Based Early Exit CNN for Energy-efficient Myocardial Infarction Detection on Low-power Wearable Devices, IMWUT
  3. Testudo: Collaborative Intelligence for Latency-Critical Autonomous Systems, IEEE TCAD

2021

  1. LENS: Layer Distribution Enabled Neural Architecture Search in Edge-Cloud Hierarchies, DAC
  2. EExNAS: Early-Exit Neural Architecture Search Solutions for Low-Power Wearable Devices, ISLPED
  3. Energy-Aware Design Methodology for Myocardial Infarction Detection on Low-Power Wearable Devices, ASP-DAC
  4. SAGE: A Split-Architecture Methodology for Efficient End-to-End Autonomous Vehicle Control, ACM TECS