SRPO refines GRPO into role-aware token-level advantages by emphasizing perception tokens based on visual dependency (original vs. corrupted inputs) and reasoning tokens based on consistency with perception, unified via a shared baseline.
Visually-Guided Policy Optimization for Multimodal Reasoning
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
abstract
Reinforcement learning with verifiable rewards (RLVR) has significantly advanced the reasoning ability of vision-language models (VLMs). However, the inherent text-dominated nature of VLMs often leads to insufficient visual faithfulness, characterized by sparse attention activation to visual tokens. More importantly, our empirical analysis reveals that temporal visual forgetting along reasoning steps exacerbates this deficiency. To bridge this gap, we propose Visually-Guided Policy Optimization (VGPO), a novel framework to reinforce visual focus during policy optimization. Specifically, VGPO initially introduces a Visual Attention Compensation mechanism that leverages visual similarity to localize and amplify visual cues, while progressively elevating visual expectations in later steps to counteract visual forgetting. Building on this mechanism, we implement a dual-grained advantage re-weighting strategy: the intra-trajectory level highlights tokens exhibiting relatively high visual activation, while the inter-trajectory level prioritizes trajectories demonstrating superior visual accumulation. Extensive experiments demonstrate that VGPO achieves better visual activation and superior performance in mathematical multimodal reasoning and visual-dependent tasks. The code has been released at https://github.com/wzb-bupt/VGPO.
years
2026 6verdicts
UNVERDICTED 6representative citing papers
VIGIL is a counterfactual RL alignment method that reduces visual hallucinations in MLLMs by enforcing visual grounding via masked attention penalties, outperforming baselines with 25% of the data and showing emergent spatial capabilities.
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.
VeriEvol decouples prompt difficulty evolution from answer reliability verification to scale verified data for visual math reasoning, lifting benchmark accuracy from 35.42 to 54.73 and adding +3.88 in GRPO RL.
MAPO is a dual-branch RL framework using modality relevance masks from cross-modal differential entropy and auxiliary attention losses to reduce late-stage modality collapse in audio reasoning models and improve benchmark results.
RISE proposes a self-evolving VLM framework with three designs to address challenges in question generation and solver adaptation, reporting consistent gains on seven benchmarks across two backbones.
citing papers explorer
-
Structured Role-Aware Policy Optimization for Multimodal Reasoning
SRPO refines GRPO into role-aware token-level advantages by emphasizing perception tokens based on visual dependency (original vs. corrupted inputs) and reasoning tokens based on consistency with perception, unified via a shared baseline.
-
Staying VIGILant: Mitigating Visual Laziness via Counterfactual Visual Alignment in MLLMs
VIGIL is a counterfactual RL alignment method that reduces visual hallucinations in MLLMs by enforcing visual grounding via masked attention penalties, outperforming baselines with 25% of the data and showing emergent spatial capabilities.
-
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.
-
VeriEvol: Scaling Multimodal Mathematical Reasoning via Verifiable Evol-Instruct
VeriEvol decouples prompt difficulty evolution from answer reliability verification to scale verified data for visual math reasoning, lifting benchmark accuracy from 35.42 to 54.73 and adding +3.88 in GRPO RL.
-
Escape the Language Prior: Mitigating Late-Stage Modality Collapse in Audio Reasoning via Modality-Aware Policy Optimization
MAPO is a dual-branch RL framework using modality relevance masks from cross-modal differential entropy and auxiliary attention losses to reduce late-stage modality collapse in audio reasoning models and improve benchmark results.
-
RISE: Reliable Improvement in Self-Evolving Vision-Language Models
RISE proposes a self-evolving VLM framework with three designs to address challenges in question generation and solver adaptation, reporting consistent gains on seven benchmarks across two backbones.