Omni-modal language models are intended to jointly understand audio, visual inputs, and language, but benchmark gains can be inflated when visual evidence alone is enough to answer a query. We study whether current omni-modal benchmarks separate visual shortcuts from genuine audio-visual-language evidence integration, and how post-training behaves under a visually debiased evaluation setting. We audit nine omni-modal benchmarks with visual-only probing, remove visually solvable queries, and retain full subsets when filtering is undefined or would make comparisons unstable. This yields OmniClean, a cleaned evaluation view with 8,551 retained queries from 16,968 audited queries. On OmniClean, we evaluate OmniBoost, a three-stage post-training recipe based on Qwen2.5-Omni-3B: mixed bi-modal SFT, mixed-modality RLVR, and SFT on self-distilled data. Balanced bi-modal SFT gives limited and uneven gains, RLVR provides the first broad improvement, and self-distillation reshapes the benchmark profile. After SFT on self-distilled data, the 3B model reaches performance comparable to, and in aggregate slightly above, Qwen3-Omni-30B-A3B-Instruct without using a stronger omni-modal teacher. These results show that omni-modal progress is easier to interpret when evaluation controls visual leakage, and that small omni-modal models can benefit from staged post-training with self-distilled omni-query supervision. Project page: https://cheliu-computation.github.io/omni/

翻译：全模态语言模型旨在联合理解音频、视觉输入与语言，但若仅凭视觉证据即可回答问题，基准测试的收益可能被夸大。本研究探讨当前全模态基准测试能否区分视觉捷径与真正的音视频-语言证据整合，以及后训练在视觉去偏评估设置下的表现。我们通过仅含视觉输入的探测方法审计了九个全模态基准测试，剔除可仅凭视觉解决的查询，并在过滤规则未定义或会导致比较不稳定的情况下保留完整子集。由此构建出OmniClean——一个经过清理的评估视图，从16,968条被审计的查询中保留了8,551条。在OmniClean上，我们评估了基于Qwen2.5-Omni-3B的三阶段后训练方案OmniBoost：混合双模态SFT、混合模态RLVR、以及基于自蒸馏数据的SFT。均衡双模态SFT带来的提升有限且不均衡，RLVR首次带来广泛改进，而自蒸馏重塑了基准测试的格局。在自蒸馏数据上完成SFT后，该3B模型在未使用更强全模态教师模型的情况下，达到了与Qwen3-Omni-30B-A3B-Instruct相当且整体略优的性能。这些结果表明：当评估过程控制了视觉信息泄露时，全模态的进步更易于解释；同时，小型全模态模型可通过分阶段后训练与自蒸馏全模态查询监督受益。项目页面：https://cheliu-computation.github.io/omni/