Booth #1113

Don’t be lazy: CompleteP enables compute-efficient deep transformers

Power Lines: Scaling Laws for Weight Decay and Batch Size in LLM Pre-training

DREAM: Drafting with Refined Target Features and Entropy-Adaptive Cross-Attention Fusion for Multimodal Speculative

PTPP-Aware Adaptation Scaling Laws: Predicting Domain-Adaptation Performance at Unseen Pre-Training Budgets

The Conductor and the Engine: A Path Towards Co-Designed Reasoning

Calibrated Reasoning: An Explanatory Verifier for Dynamic and Efficient Problem-Solving