Continual Harness: Online Adaptation for Self-Improving Foundation Agents Paper • 2605.09998 • Published May 11 • 19
The PokeAgent Challenge: Competitive and Long-Context Learning at Scale Paper • 2603.15563 • Published Mar 16 • 12
Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement Learning Paper • 2605.00347 • Published May 1 • 16
COMPACT: COMPositional Atomic-to-Complex Visual Capability Tuning Paper • 2504.21850 • Published Apr 30, 2025 • 27
Unifying Specialized Visual Encoders for Video Language Models Paper • 2501.01426 • Published Jan 2, 2025 • 20
