{"ID":5675130,"CreatedAt":"2026-07-03T01:40:09.565152011Z","UpdatedAt":"2026-07-05T04:57:17.014105577Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.01707","arxiv_id":"2607.01707","title":"LASER: A Corrective Lens for LVLMs via Visual Attention Preservation and Sink Suppression","abstract":"Large vision-language models (LVLMs) exhibit strong reasoning ability but suffer from visual forgetting during long-horizon decoding, where attention progressively drifts away from visual evidence. Existing methods largely treat this issue as a late-stage attention decay problem or attempt to mitigate it through heuristic reminders or post-hoc attention lifting. Through systematic empirical analysis, we find that performance degradation under visual forgetting is largely driven by two overlooked factors: early-stage attention decay disrupts evidence acquisition, and attention concentration on a subset of task-irrelevant visual sink tokens. Motivated by these insights, we propose LASER, a post-training framework that regulates both the visual attention trajectory and intra-visual token attention distribution during reasoning. Technically, LASER introduces two complementary rewards: a Visual Grounding Reward, which encourages the model to maintain attention on semantically salient visual tokens throughout decoding, and a Sink Suppression Reward, which penalizes excessive attention concentration on visual sink tokens. Together, these rewards preserve early-stage grounding while preventing attention collapse onto uninformative regions. Extensive experiments on eight benchmark datasets demonstrate that LASER consistently outperforms strong baselines, validating attention-aware training as an effective remedy for visual forgetting.","short_abstract":"Large vision-language models (LVLMs) exhibit strong reasoning ability but suffer from visual forgetting during long-horizon decoding, where attention progressively drifts away from visual evidence. Existing methods largely treat this issue as a late-stage attention decay problem or attempt to mitigate it through heuris...","url_abs":"https://arxiv.org/abs/2607.01707","url_pdf":"https://arxiv.org/pdf/2607.01707v1","authors":"[\"Bowen Yuan\",\"Zijian Wang\",\"Yadan Luo\",\"Shijie Wang\",\"Zi Huang\"]","published":"2026-07-02T04:59:56Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Language Model\"]","has_code":false}