8 papers
DAVE: A VLM Vision Encoder for Document Understanding and Web Agents
Brandon Huang, Hang Hua, Zhuoran Yu +3
While Vision-language models (VLMs) have demonstrated remarkable performance across multi-modal tasks, their choice of vision encoders presents a fundamental weakness: their low-le…
Mechanistic Finetuning of Vision-Language-Action Models via Few-Shot Demonstrations
Chancharik Mitra, Yusen Luo, Raj Saravanan +7
Vision-Language Action (VLAs) models promise to extend the remarkable success of vision-language models (VLMs) to robotics. Yet, unlike VLMs in the vision-language domain, VLAs for…
Do What? Teaching Vision-Language-Action Models to Reject the Impossible
Wen-Han Hsieh, Elvis Hsieh, Dantong Niu +3
Recently, Vision-Language-Action (VLA) models have demonstrated strong performance on a range of robotic tasks. These models rely on multimodal inputs, with language instructions p…
Activation Reward Models for Few-Shot Model Alignment
Tianning Chai, Chancharik Mitra, Brandon Huang +8
Aligning Large Language Models (LLMs) and Large Multimodal Models (LMMs) to human preferences is a central challenge in improving the quality of the models' generative outputs for…
LeVERB: Humanoid Whole-Body Control with Latent Vision-Language Instruction
Haoru Xue, Xiaoyu Huang, Dantong Niu +8
Vision-language-action (VLA) models have demonstrated strong semantic understanding and zero-shot generalization, yet most existing systems assume an accurate low-level controller…
Visualizing Thought: Conceptual Diagrams Enable Robust Planning in LMMs
Nasim Borazjanizadeh, Roei Herzig, Eduard Oks +3
Human reasoning relies on constructing and manipulating mental models -- simplified internal representations of situations used to understand and solve problems. Conceptual diagram…