CIViC: Evidence Gates for Audio-Conditioned Visual Prediction on Proxy Tasks
CIViC: Evidence Gates for Audio-Conditioned Visual Prediction on Proxy Tasks
CIViC提出由四道關卡組成的檢查協議,用以評估音訊條件視覺預測是否運用了預期的音訊資訊。合成音訊特徵混合任務中,加入條件的模型在 1,000 步時 RMSE 為 0.1807,高於僅用音訊模型的 0.1707;SpeakerVid 代理任務中,五項低階音訊摘要歸零的模型整體影格灰階 RMSE 較低,但對齊音訊的片段漂移誤差較低。結果顯示,不同代理任務中的輸出啟動、留出誤差及端點控制支持不同解讀。
Published on Oct 11
Authors:
,
,
,
,
,
Abstract
Removing audio can shift a visual predictor's output without showing whether the task uses the intended audio information. We introduce Conditional Input and Visual Interpretation Checks (CIViC), a four-gate protocol that links an interpretation to an intervention, held-out task comparison, or endpoint control. We demonstrate CIViC on actor-disjoint face-raster tests, a synthetic audio-feature mixture, and source-video-disjoint SpeakerVid proxy tasks. In the static face-raster test, cross-actor audio replacement meets the registered detection rule with a small effect; on a separate temporal endpoint, constant-audio fits score better than audio-trained fits in four matched seeds. In the synthetic mixture, the condition-augmented fit has higher 1,000-step RMSE than the audio-only fit (0.1807 vs. 0.1707), with the gap shrinking during training. In the SpeakerVid proxy, the five-feature-zero fit (five low-level audio summaries zeroed; identity, dialogue, and condition inputs retained) has lower whole-frame grayscale RMSE than aligned audio across four held-out conditions and five paired seeds, while aligned audio has lower segment-drift error. The results show that output activation, held-out error, and endpoint controls support different interpretations across these proxy tasks.
View arXiv page View PDF GitHub Add to collection
Get this paper in your agent:
hf papers read 2610.15327
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2610.15327 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2610.15327 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.15327 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co