MolmoB0T: Large-Scale Simulation Enables Zero-Shot Manipulation
MolmoB0T is a suite of general-purpose robotic manipulation policies trained on 2.5 million simulated trajectories that achieve state-of-the-art zero-shot transfer to diverse real-world tasks and environments.
Jun 5, 2026
MolmoPoint: Better Pointing for VLMs with Grounding Tokens
MolmoPoint is a new VLM architecture that enables more precise and efficient visual grounding by using special tokens to directly select from the model's internal visual representation instead of generating text coordinates.
Jun 4, 2026
Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding
Molmo2 is a new family of open-source video-language models that achieve state-of-the-art performance through novel datasets and training methods, particularly excelling in video grounding tasks without relying on proprietary models.
Jun 3, 2026
Unified Spatio-Temporal Token Scoring for Efficient Video VLMs
STTS is a novel, simple yet effective technique for unified, architecture-wide vision token pruning across both ViT and LLM, improving efficiency by 62% with minimal performance loss in video QA tasks.
Mar 18, 2026
ASAP-NMS: Accelerating Non-Maximum Suppression Using Spatially Aware Priors
Jul 19, 2020
RSO: A Gradient Free Sampling Based Approach For Training Deep Neural Networks
May 12, 2020