PPaperPicks

Weigao Sun

9 papers at tracked venues · 8 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Native Hybrid Attention for Efficient Sequence Modeling
  2. Nirvana: A Specialized Generalist Model With Task-Aware Memory Mechanism
  3. CogniBench: A Legal-inspired Framework and Dataset for Assessing Cognitive Faithfulness of Large Language Models
  4. Improving Bilinear RNN with Closed-loop Control
  5. Liger: Linearizing Large Language Models to Gated Recurrent Structures
  6. Sequence Accumulation and Beyond: Infinite Context Length on Single GPU and Large Clusters
    AAAI 2025 · Weigao Sun
  7. CO2: Efficient Distributed Training with Full Communication-Computation Overlap
    ICLR 2024 · Weigao Sun
  8. Scaling Laws for Linear Complexity Language Models
  9. Various Lengths, Constant Speed: Efficient Language Modeling with Lightning Attention