- formatting
- images
- links
- math
- code
- blockquotes
- external-services
•
•
•
•
•
•
-
In-Context Distillation with Self-Consistency Cascades: A Simple, Training-Free Way to Reduce LLM Agent Costs
-
Improving Online Algorithms via ML Predictions
-
Improving Context Fidelity via Native Retrieval-Augmented Reasoning
-
Improved Baselines with Visual Instruction Tuning
-
Imbalanced Gradients in RL Post-Training of Multi-Task LLMs