AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Towards Spatial Trace with Reasoning in Vision-Language Models for Robotics

Enshen Zhou, Yibo Li, Jingkun An, Jiayuan Zhang, Shanyu Rong, Mengzhen Liu, Yi Han, Yuheng Ji, Huajie Tan, Jiawei He, Pengwei Wang, Zhongyuan Wang and 3 more

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Spatial reasoning in VLMs · 22 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add 2D data to SFT data recipe (ablation)RoboTracer-2B SFT · Q-SpatialSR: 51.49 -> 69.61Improved
add 3D data to SFT data recipe (ablation)RoboTracer-2B SFT · Q-SpatialSR: 33.52 -> 69.61Improved
add video data to SFT data recipe (ablation)RoboTracer-2B SFT · ShareRobotBenchDiscrete Frechet Distance: 0.4376 -> 0.1605Improved
add regression-supervised scale decoder instead of no scale supervision (ablation)RoboTracer-2B SFT · Q-SpatialSR: 53.47 -> 69.61Improved
use regression instead of next-token prediction for scale supervision (ablation)RoboTracer-2B SFT · Q-SpatialSR: 57.43 -> 69.61Improved
model points as (u,v,d) instead of (x,y,z) (ablation)RoboTracer-2B SFT · ShareRobotBenchDiscrete Frechet Distance: 0.2426 -> 0.1605Improved
model points as (u,v,d) instead of (x,y,z) (ablation)RoboTracer-2B SFT · TraceSpatial-BenchSR: 30 -> 31Improved
add universal spatial encoder before RFT (ablation)RoboTracer-2B RFT · TraceSpatial-BenchSR: 36 -> 39Improved
add RFT after SFTRoboTracer-2B · TraceSpatial-BenchSR: 31 -> 39Improved
add metric-sensitive process reward in RFT (ablation)RoboTracer-RFT · TraceSpatial-Benchoverall SR: 33 -> 39Improved
add camera intrinsics and absolute depth input to RFT modelRoboTracer-RFT · TraceSpatial-Benchoverall SR: 39 -> 45Improved
add noise to depth inputRoboTracer-RFT · TraceSpatial-Benchoverall SR: 45 -> 44No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy