← authors · overview

• Setting The Trap: Capturing And Defeating Backdoors In Pretrained Language Models Through Honeypots
  2023 · 1 citations
• AutoL2S: Auto Long-Short Reasoning for Efficient Large Language Models
  2025
• Deterministic Inference across Tensor Parallel Sizes That Eliminates Training-Inference Mismatch
  2025
• BLASST: Dynamic BLocked Attention Sparsity via Softmax Thresholding
  2025
• Deterministic Inference across Tensor Parallel Sizes That Eliminates Training-Inference Mismatch
  2025
• Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference
  2025
• Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models
  2025
• Give Me FP32 or Give Me Death? Challenges and Solutions for Reproducible Reasoning
  2025
• Interpreting and Steering LLMs with Mutual Information-based Explanations on Sparse Autoencoders
  2025
• Taylor Unswift: Secured Weight Release for Large Language Models via Taylor Expansion
  2024
• Robot Learning with Super-Linear Scaling
  2024