Into the Unknown: Benchmarking AI agents on open scientific research problems Paper • 2610.19159 • Published 24 days ago • 56
PUBG Ally: A Conversational Embodied Agent as an AI Teammate Paper • 2609.29837 • Published Sep 24 • 12
Can Large Language Models Keep Up? Benchmarking Online Adaptation to Continual Knowledge Streams Paper • 2603.07392 • Published Mar 8 • 18
The Coverage Principle: A Framework for Understanding Compositional Generalization Paper • 2505.20278 • Published May 26, 2025 • 7
TokenButler Collection TokenButler -- Predict token importance for all heads across the transformer in the first layer itself. Enable fine-grained token sparsity! • 6 items • Updated Mar 11, 2025 • 3
Investigating How Large Language Models Leverage Internal Knowledge to Perform Complex Reasoning Paper • 2406.19502 • Published Jun 27, 2024 • 2
Aligning to Thousands of Preferences via System Message Generalization Paper • 2405.17977 • Published May 28, 2024 • 7