Irina Rish

$\mu$LO: Compute-Efficient Meta-Generalization of Learned Optimizers

On the Adversarial Robustness of Discrete Image Tokenizers

On the Emergence of Reasoning

Indirect Prompt Injections: Are Firewalls All You Need, or Stronger Benchmarks?

Deep Neural Networks Divide and Conquer Dihedral Multiplication

Unified Neural Scaling Laws

Surprising Effectiveness of pretraining Ternary Language Model at Scale

Enabling Realtime Reinforcement Learning at Scale with Staggered Asynchronous Inference

AI for Global Climate Cooperation: Modeling Global Climate Negotiations, Agreements, and Long-Term Cooperation in RICE-N

Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced Reasoning

Handling Delay in Real-Time Reinforcement Learning

Context is Key: A Benchmark for Forecasting with Essential Textual Information

Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching

$\mu$LO: Compute-Efficient Meta-Generalization of Learned Optimizers

Context is Key: A Benchmark for Forecasting with Essential Textual Information

Robin: a Suite of Multi-Scale Vision-Language Models and the CHIRP Evaluation Benchmark

Unmasking the Version-Switching Capabilities of Code Generation Models