Bridging Physical Reasoning and Task Generalization via Visual Action Outcome Reasoning Alignment
Vision-language models (VLMs) struggle to generalize in interactive physical reasoning, particularly under unseen tasks and environments. Two key failure modes are prominent: hallucinated chain-of-thought (CoT) reasoning that contradicts physical reality, and misalignment between the model's reasoning and actions. We present VAORA (Visual Action Outcome Reasoning Alignment), a novel reward design that directly addresses both issues. VAORA introduces two complementary rewards: Visual Alignment Reward, which anchors VLM reasoning to the visual context independent of the agent action itself, and
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 50%Alignment →
- LinkedLinked via arxiv author · 85%Han-Jun Ko →
“Bridging Physical Reasoning and Task Generalization via Visual Action Outcome Reasoning Alignment”
- LinkedLinked via arxiv author · 85%Jr-Jen Chen →
“Bridging Physical Reasoning and Task Generalization via Visual Action Outcome Reasoning Alignment”
- LinkedLinked via arxiv author · 85%Haobo Yuan →
“Bridging Physical Reasoning and Task Generalization via Visual Action Outcome Reasoning Alignment”
- LinkedLinked via arxiv author · 85%Hsin-Ying Lee →
“Bridging Physical Reasoning and Task Generalization via Visual Action Outcome Reasoning Alignment”
- LinkedLinked via arxiv author · 85%Tiancheng Shen →
“Bridging Physical Reasoning and Task Generalization via Visual Action Outcome Reasoning Alignment”
- LinkedLinked via arxiv author · 85%Ming-Hsuan Yang →
“Bridging Physical Reasoning and Task Generalization via Visual Action Outcome Reasoning Alignment”
- LinkedLinked via arxiv author · 85%Yu-Chiang Frank Wang →
“Bridging Physical Reasoning and Task Generalization via Visual Action Outcome Reasoning Alignment”