NITP: Next Implicit Token Prediction for LLM Pre-training Paper • 2605.24956 • Published 19 days ago • 35
GridProbe: Posterior-Probing for Adaptive Test-Time Compute in Long-Video VLMs Paper • 2605.10762 • Published May 11 • 3
view article Article You could have designed state of the art positional encoding FL33TW00D-HF • Nov 25, 2024 • 485
VideoAtlas: Navigating Long-Form Video in Logarithmic Compute Paper • 2603.17948 • Published Mar 18 • 3
Vote-in-Context: Turning VLMs into Zero-Shot Rank Fusers Paper • 2511.01617 • Published Nov 3, 2025 • 3