← authors · overview

• LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding
  2024 · 26 citations
• Experience Graphs: The Data Foundation for Self-Improving Agents
  2026
• Agentic Discovery of Neural Architectures: AIRA-Compose and AIRA-Design
  2026
• Gecko: An Efficient Neural Architecture Inherently Processing Sequences with Arbitrary Lengths
  2026
• Hybrid Architectures for Language Models: Systematic Analysis and Design Insights
  2025
• Cross-Stack Workload Characterization of Deep Recommendation Systems
  2020
• Understanding Capacity-Driven Scale-Out Neural Recommendation Inference
  2020
• Low-Precision Hardware Architectures Meet Recommendation Model Inference at Scale
  2021
• On Sampling Collaborative Filtering Datasets
  2022
• RecD: Deduplication for End-to-End Deep Learning Recommendation Model Training Infrastructure
  2022
• FlexShard: Flexible Sharding for Industry-Scale Sequence Recommendation Models
  2023
• MP-Rec: Hardware-Software Co-Design to Enable Multi-Path Recommendation
  2023