CoFL-S: Shaping the Future of Vision-Language Navigation
CoFL-S introduces a new low-level action framework in vision-language navigation, outperforming traditional models. It redefines how robots understand and execute complex instructions.
Read the full articleYou might also wanna read
Using Vision-Language Models to Segment Robot Demonstration Videos into Subtask Annotations
A benchmark and field report on using VLMs to turn robot and egocentric video into timestamped subtask annotations.
macrodata.co·12d ago
DILLO: A Language-Based World Model for Proactive Agent Steering Without Visual Simulation
Deploying safety-critical agents requires anticipating the consequences of actions before they are executed. While world models offer a para
arxiv.org·19d ago
LLM-Based Framework Translates Natural Language into Spacecraft Trajectory Optimization Code
Trajectory optimization is a critical component for enabling safe and reliable autonomous operations in space exploration. As space missions
arxiv.org·1mo ago
ReMoT: A Reinforcement Learning Framework Using Motion Contrast Triplets to Improve VLM Spatio-Temporal Reasoning
We present ReMoT, a unified training paradigm to systematically address the fundamental shortcomings of VLMs in spatio-temporal consistency
arxiv.org·29d ago
GLM-5V-Turbo: A Native Multimodal Foundation Model for Agentic AI Tasks
We present GLM-5V-Turbo, a step toward native foundation models for multimodal agents. As foundation models are increasingly deployed in rea
arXiv.org·2mo ago
SRTF: A Simple Robot Training Format for Vision-Action Model Datasets
A Simple Robot Training Format. Contribute to tetra-dynamics/srtf development by creating an account on GitHub.
github.com·10d ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.