← authors · overview

• ECO: Quantized Training without Full-Precision Master Weights
  2026
• Memory Caching: RNNs with Growing Memory
  2026
• Theoretical Perspectives on Data Quality and Synergistic Effects in Pre- and Post-Training Reasoning Models
  2026
• Data Selection for Fine-tuning Vision Language Models via Cross Modal Alignment Trajectories
  2025
• Understanding the Role of Training Data in Test-Time Scaling
  2025
• Gemma 3 Technical Report
  2025
• It's All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online Optimization
  2025
• ATLAS: Learning to Optimally Memorize the Context at Test Time
  2025
• Nested Learning: The Illusion of Deep Learning Architectures
  2025
• Efficient Data Selection at Scale via Influence Distillation
  2025
• Contextual Bandits with Cross-learning
  2018
• HyperAttention: Long-context Attention in Near-Linear Time
  2023