SPOT-E这个新方法挺有意思，它不重训模型，只在推理时搞了个视觉聚光灯和熵整形，就让VLM在那些需要细看局部证据的任务上表现好多了。尤其用GRPO调优，效果提升还挺稳定。
SPOT-E方法针对视觉语言模型在处理证据密集型任务时因小区域视觉证据被忽略导致的读取失败问题。该方法利用答案跨度预测熵作为模型内部反馈，通过低熵锚点和熵整形目标消除歧义，避免模型陷入捷径塌缩。SPOT-E基于GRPO进行每实例轻量级调优，生成问题条件化的聚光灯。在多个VLM族和基准测试中，SPOT-E一致提升了性能并增强了视觉损坏鲁棒性。代码已开源。
SPOT-E: Test-Time Entropy Shaping with Visual Spotlights for Frozen VLMs
Vision-language models (VLMs) often underperform on evidence intensive tasks because decisive visual evidence are small, localized, and easy to overlook, leading to failures in evidence readout even when high-level reasoning is intact. Prior inference-time visual interventions can improve grounding without retraining, but they are largely open-loop and lack a mechanism to verify whether highlighted evidence is actually used. We study answer-span prediction entropy as a model-internal feedback signal and show that naive entropy minimization is ambiguous, since low entropy may arise from evidence-grounded confidence or shortcut collapse. To resolve this ambiguity, we introduce low-entropy anchors and an entropy-shaping objective that reduces answer uncertainty while preserving baseline high-confidence tokens. We instantiate this principle in SPOT-E, a plug-and-play test-time method that produces question-conditioned spotlights, optimized per instance via light-weight tuning based on Group Relative Policy Optimization (GRPO). Across all benchmarks and different VLM families, SPOT-E yields consistent gains and improved robustness under visual corruptions. Code is publicly available at: \url{https://github.com/YinBo0927/SPOT-E}