• The False Dawn: Reevaluating Google's Reinforcement Learning for Chip Macro Placement
• Extending Context Window of Large Language Models via Positional Interpolation
• CLIPA-v2: Scaling CLIP Training with 81.1% Zero-shot ImageNet Accuracy within a $10,000 Budget; An Extra $4,000 Unlocks 81.8% Accuracy
• LeanDojo: Theorem Proving with Retrieval-Augmented Language Models

Support the show