FineVLA: Fine-Grained Instruction Alignment For VLA - a xlangai Collection

xlangai 's Collections

FineVLA: Fine-Grained Instruction Alignment For VLA

CUA-Gym: Scaling Verifiable Training Environments and Tasks

OpenCUA: Open Foundations for Computer-Use Agents

FineVLA: Fine-Grained Instruction Alignment For VLA

updated Jun 4

This is the collection of FineVLA, including the RoboFine-Bench RoboFine-VLM and FineVLA-policyLA

xlangai/RoboFine-bench

Viewer • Updated Jul 5 • 1k • 1.52k • 5
xlangai/RoboFine-VLM-397B-A17B

Video-Text-to-Text • 403B • Updated Jul 5 • 207 • 8
FineVLA: Fine-Grained Instruction Alignment for Steerable Vision-Language-Action Policies

Paper • 2605.27284 • Published May 26 • 9