JUMP 2.0 Best Papers

Each quarter, the JUMP 2.0 Centers identify the single best publication (i.e. top paper) from their research efforts. The papers are listed below, categorized by Center with the most recent contribution at the top.

2024

 ACE

  • Quarter 1: 310454: Caravan: Practical Online Learning of In-Network ML Models with Labeling Agents
  • Quarter 2: 321758: Allo: A Programming Model for Composable Accelerator Design
  • Quarter 3: 382480: ReCycle: Pipeline Adaptation for the Resilient Distributed Training of Large DNNs

CHIMES: 

  • Quarter 1: 325398Achieving a High Thermally Conductive One Micron AlN Deposition by High Power Impulse Magnetron Sputtering Plus Kick
  • Quarter 2: 402032ALT-Lock: Logic and Timing Ambiguity-Based IP Obfuscation Against Reverse Engineering
  • Quarter 3: 272062Glass Package with Multiple Embedded Dies for mm Wave Applications IEEE Transactions on Components, Packaging and Manufacturing Technology

COCOSYS

  • Quarter 1: 291359: CogSys: Efficient and Scalable Neurosymbolic Cognition System via Algorithm-Hardware Co-Design
  • Quarter 2: 311877: A Dynamic Power-only Compute-In-Memory Macro with Power-of-Two Nonlinear SAR ADC for Non-volatile Ferroelectric Capacitive Crossbar Array
  • Quarter 3: 395260: Towards Efficient Neuro-Symbolic AI: From Workload Characterization to Hardware Architecture

COGNISENSE

CUBIC

  • Quarter 1: 291112: 140-GHz 2-D Scalable On-Grid 8 x 8-Element Transmit–Receive Phased Arrays With Up/Down Converters Demonstrating a 5.2-m Link at 16 Gbps
  • Quarter 2: 346777: Characterizing Sub-Terahertz Reflection and Its Impact on Next-Generation Wireless Networking
  • Quarter 3: 379514: Enhancing the Accuracy of 6T SRAM-based In-Memory Architecture via Maximum Likelihood Detection

PRISM

  • Quarter 1: 306175: NeuroSim V1.4: Extending technology support for digital compute-in-memory towards 1nm node
  • Quarter 2: 306543: TAPA-CS: Enabling Scalable Accelerator Design on Distributed HBM-FPGAs
  • Quarter 3: 383127: “UFC: A Unified Accelerator for Fully Homomorphic Encryption”, IEEE/ACM International Symposium on Microarchitecture 

SUPREME

  • Quarter 1: 310555: CMOS-Compatible Strain Engineering for High-Performance Monolayer Semiconductor Transistors
  • Quarter 2: 306589: High-throughput ab initio screening of 2D materials identifies p-type monolayer WS2 as potential ultra-high mobility semiconductor 
  • Quarter 3: 399389: Enabling P-type Conduction in Bilayer WS2 with NbP Topological Semimetal Contacts

 

2023

 ACE

  • Quarter 3: 205910CC-NIC: a Cache-Coherent Interface to the NIC 

CHIMES: 

  • Quarter 3: 199353: H3DAtten Heterogeneous 3D Integrated Hybrid Analog and Digital Compute-in-Memory Accelerator for Vision Transformer Self-Attention

COCOSYS

  • Quarter 3: 206878: GPT4AIGChip: Towards Next-Generation AI Accelerator Design Automation via Large Language Models

COGNISENSE

  • Quarter 3: 189124An 18.6-dBm, 8-way-combined D-band Power Amplifier with 21.6% PAE in 22-nm FD-SOI CMOS

CUBIC

  • Quater 3: 199103: N-Polar GaN Deep Recess HEMT with Atomic Layer Deposition HfO2 as Gate Insulator

PRISM

  • Quater 3: 202291Demystifying CXL Memory with Genuine CXL-Ready Systems and Devices

SUPREME

  • Quarter 3: 210082: Invited Paper: Algorithm/Hardware Co-design for Few-Shot Learning at the Edge

4819 Emperor Blvd, Suite 300 Durham, NC 27703 Voice: (919) 941-9400 Fax: (919) 941-9450

Important Information for the SRC website. This site uses cookies to store information on your computer. By continuing to use our site, you consent to our cookies. If you are not happy with the use of these cookies, please review our Cookie Policy to learn how they can be disabled. By disabling cookies, some features of the site will not work.