Filter papers
From Tools to Teammates: Evaluating LLMs in Multi-Session Coding Interactions
Code
Collaboration
Evaluation
Reasoning
Tooling
Code
Collaboration
Evaluation
Reasoning
Tooling
Policy Primer - Efficient AI
AI Policy
Compute
Data Efficiency
Model Compression
AI Policy
Compute
Data Efficiency
Model Compression
Fairness of Deep Ensembles: On the interplay between per-group task difficulty and under-representation
Computer Vision
Responsible AI
Computer Vision
Responsible AI
Policy Primer - Translating Safety
AI Policy
multilingual
Safety
AI Policy
multilingual
Safety
If You Can't Use Them, Recycle Them
Language Models
Optimization
Language Models
Optimization
Aya Expanse: Combining Research Breakthroughs for a New Multilingual Frontier
multilingual
Language Models
multilingual
Language Models
Global MMLU
Evaluation
Open Source
multilingual
Generative Models
Evaluation
Open Source
multilingual
Generative Models
The Reality of AI and Biorisk
AI Policy
Responsible AI
Safety
AI Policy
Responsible AI
Safety
INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge
Data
Evaluation
Generative Models
multilingual
Open Source
Language Models
Data
Evaluation
Generative Models
multilingual
Open Source
Language Models
Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models
Reasoning
Pre-Training
Data
Interpretability
Reasoning
Pre-Training
Data
Interpretability
M-RewardBench: Evaluating Reward Models in Multilingual Settings
multilingual
Data
Evaluation
Open Release
Collaboration
multilingual
Data
Evaluation
Open Release
Collaboration
Mix Data or Merge Models? Optimizing for Diverse Multi-Task Learning
multilingual
Safety
Supervised Learning
Language
Human Feedback
Efficiency
multilingual
Safety
Supervised Learning
Language
Human Feedback
Efficiency
Diversify and Conquer: Diversity-Centric Data Selection with Iterative Refinement
Language Models
Data
Data Efficiency
Data Pruning
Language Models
Data
Data Efficiency
Data Pruning
AI Policy
Safety
Mixture of Experts
Multilingual Arbitrage: Optimizing Data Pools to Accelerate Multilingual Progress
Language
Robustness
Mixture of Experts
Language
Robustness
Mixture of Experts
Light bulbs have energy ratings — so why can’t AI chatbots?
Language Models
Efficiency
Language Models
Efficiency
To Code, or Not To Code? Exploring Impact of Code in Pre-training
Continual Learning
Code
Pre-Training
Continual Learning
Code
Pre-Training