PPaperPicks

Christopher De Sa

10 papers at tracked venues · 9 at CORE A* · active 20242025

Venues

Frequent coauthors

Papers

  1. Compute-Optimal LLMs Provably Generalize Better with Scale
  2. Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research
  3. Zeroth-Order Fine-Tuning of LLMs with Transferable Static Sparsity
  4. Arbitrariness and Social Prediction: The Confounding Role of Variance in Fair Classification
  5. Diffusion Models With Learned Adaptive Noise
  6. Proceedings of the Seventh Annual Conference on Machine Learning and Systems, MLSys 2024, Santa Clara, CA, USA, May 13-16, 2024
  7. QTIP: Quantization with Trellises and Incoherence Processing
  8. QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks
  9. Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices
  10. Shadow Cones: A Generalized Framework for Partial Order Embeddings