P2R decouples perception from reasoning in VLMs via a two-stage process and PRA-GRPO alternating RL training, reporting gains such as 93.2% on V-Star for the 4B model over its Qwen3-VL backbone.
arXiv preprint arXiv:2602.12916 , year=
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
baseline 1
citation-polarity summary
fields
cs.CV 5years
2026 5representative citing papers
TTSP samples and filters multiple zoom-in exploration traces and iteratively consolidates validated observations into an Evidence Ledger, improving fine-grained multimodal reasoning on V* Bench, HR-Bench, TreeBench, and MME-RealWorld-Lite.
MAPO improves multimodal chain-of-thought reasoning by requiring explicit textual descriptions of visual tool results and using a novel advantage estimator that combines semantic alignment with task rewards.
V-Zero trains MLLMs for visual reasoning without answer labels by gating on-policy distillation trajectories using contrastive evidence from relevant versus negative image crops.
DeFakerOne is a unified foundation model for joint image-level fake image detection and pixel-level localization that reports SOTA results on 39 detection and 9 localization benchmarks.
citing papers explorer
-
Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning
P2R decouples perception from reasoning in VLMs via a two-stage process and PRA-GRPO alternating RL training, reporting gains such as 93.2% on V-Star for the 4B model over its Qwen3-VL backbone.
-
Test-time Scaling over Perception: Resolving the Grounding Paradox in Thinking with Images
TTSP samples and filters multiple zoom-in exploration traces and iteratively consolidates validated observations into an Evidence Ledger, improving fine-grained multimodal reasoning on V* Bench, HR-Bench, TreeBench, and MME-RealWorld-Lite.
-
Walk the Talk: Bridging the Reasoning-Action Gap for Thinking with Images via Multimodal Agentic Policy Optimization
MAPO improves multimodal chain-of-thought reasoning by requiring explicit textual descriptions of visual tool results and using a novel advantage estimator that combines semantic alignment with task rewards.
-
V-Zero: Answer-Label-Free On-Policy Distillation with Contrastive Evidence Gating for Fine-Grained Visual Reasoning
V-Zero trains MLLMs for visual reasoning without answer labels by gating on-policy distillation trajectories using contrastive evidence from relevant versus negative image crops.
-
Venus-DeFakerOne: Unified Fake Image Detection & Localization
DeFakerOne is a unified foundation model for joint image-level fake image detection and pixel-level localization that reports SOTA results on 39 detection and 9 localization benchmarks.