Brando Miranda

Pretraining Scaling Laws for Generative Evaluations of Language Models

ZIP-FIT: Embedding-Free Data Selection via Compression-Based Alignment for Code

CoDaPO: Confidence and Difficulty-Adaptive Policy Optimization for Language Models

Curating High Quality Pretraining Data for Language Models via Compression Ratios

Evaluating the Robustness of Chinchilla Compute-Optimal Scaling

VeriBench: End-to-End Formal Verification Benchmark for AI Code Generation in Lean 4

Data Alignment Predicts Language Model Performance: Evidence from Controlled Experiments in Autoformalization

Failures to Find Transferable Image Jailbreaks Between Vision-Language Models

Putnam-AXIOM: A Functional & Static Benchmark for Measuring Higher Level Mathematical Reasoning in LLMs

Putnam-AXIOM: A Functional & Static Benchmark for Measuring Higher Level Mathematical Reasoning in LLMs

Why Has Predicting Downstream Capabilities of Frontier AI Models with Scale Remained Elusive?

Synthetic Theorem Generation in Lean

Why Has Predicting Downstream Capabilities of Frontier AI Models with Scale Remained Elusive?

ZIP-FIT: Embedding-Free Data Selection via Compression-Based Alignment

Beyond Scale: The Diversity Coefficient as a Data Quality Metric for Variability in Natural Language Data

Lean-ing on Quality: How High-Quality Data Beats Diverse Multilingual Data in AutoFormalization