Where and Why is Grounded Reasoning Useful?
David Yan, Le Xue, Forrest Huang, Qiuyi Zhang, Dustin Tran, Andrew M. Dai, Yinfei Yang
Abstract
Grounded reasoning, where a model outputs text coordinates of relevant locations in chain-of-thought reasoning, is a common strategy for solving complex visual reasoning problems. However, the benefits and limitations of grounded reasoning are understudied. We study where and why grounded reasoning is most useful. To do so, we introduce a chain-of-thought analysis method to measure how much a model uses its outputted grounding in its thinking trace and perform a detailed ablation study of a grounded reasoning training recipe. We find that grounded reasoning improves counting but shows no significant gain over baselines without coordinate grounding across a wide range of spatial reasoning and perception benchmarks. Using several synthetic tasks, we show that grounded reasoning is most useful when a task requires undescribable references, which are visual concepts that are difficult to describe in language. However, we observe that many existing visual reasoning benchmarks are solvable with only describable text references. To close this gap, we introduce BrickVision, a new benchmark that requires undescribable visual references to solve.
Create a lesson
Related papers
Posterior Matching Distillation
Hidir Yesiltepe, Julius Berner, Arash Vahdat et al.
RL Post-Training in Diffusion Transformers Is Activation Steering
Tuna Han Salih Meral, Kaan Oktay, Alec Helbling et al.
One Prior, Two Dynamics: Repurposing Video Diffusion Transformers for Self-Supervised Latent Action Learning
Yuxin Jiang, Wenqiang Sun, Jiaqi Li et al.
ScaleWorld: High-Resolution World Generation through Shared Prediction and Refinement
Yansong Qu, Wesker Zheng, Quanjian Song et al.
Depth Pro 2: Sharp and Temporally Consistent Metric Monocular Depth
Peiyun Hu, Marko Mihajlovic, Lyndon Duong et al.
Coda-DaVinci: Reimagining Video Generation with Code2Video
Yiyan Ji, Qixun Wang, Yang Shi et al.