The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
DeepStack: Deeply Stacking Visual Tokens is Surprisingly Simple and Effective for LMMs
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
DeepStack cross-layer feature injection reduces the bottleneck of relying on a single final-layer representation and preserves acoustic evidence at different granularities, including low-level time-frequency patterns, transient events, prosodic cues, and high-level semantic information.
“This reduces the bottleneck of relying on a single final-layer representation and preserves acoustic evidence at different granularities, including low-level time-frequency patterns, transient events, prosodic cues, and high-level semantic information [11, 17].”
From MOSS-Audio Technical Report (2026) · cites this paper as [17]
MOSS-Audio adopts DeepStack-style cross-layer feature injection, which exposes multiple encoder depths to the language-model backbone.
“To preserve acoustic information across levels of abstraction, we adopt DeepStack-style cross-layer feature injection, which exposes multiple encoder depths to the language-model backbone [17, 22].”
From MOSS-Audio Technical Report (2026) · cites this paper as [17]
DeepStack injects additional visual token features into intermediate language-model layers.
“DeepStack [17] injects additional visual token features into intermediate language-model layers”
From MOSS-Audio Technical Report (2026) · cites this paper as [17]
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
LLaMA: Open and Efficient Foundation Language Models
Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozière, B., Goyal, N., Hambro, E., Azhar, F., et al. (2023) · arXiv · doi:10.48550/arxiv.2302.13971 · Cited by 4,602
Gunasekar, S., Zhang, Y., Aneja, J., Mendes, C. C. T., Del Giorno, A., Gopi, S., Javaheripi, M., Kauffmann, P., de Rosa, G., Saarikivi, O., et al. (2023) · arXiv · doi:10.48550/arxiv.2306.11644 · Cited by 138
Flagged first, then by citations
Cited by
Sorted by citations
Bai, S., Cai, Y., Chen, R., Chen, K., Chen, X., Cheng, Z., Deng, L., Ding, W., Gao, C., Ge, C., et al. (2025) · arXiv · doi:10.48550/arxiv.2511.21631 · Cited by 27
Self-citationYang, C., Yu, C., Chen, H., Zhu, J., Chen, J., Chen, K., Wang, W., Wang, Y., Jiang, Y., Jiang, Y., et al. (2026) · arXiv · doi:10.48550/arxiv.2606.01802
Self-citationEnhancing Vision Foundation Models via Multimodal Continual Pre-Training
Chen, Y., Meng, L., Peng, W., Tao, J., Xu, C., Wu, Z., & Jiang, Y.-G. (2025) · arXiv · doi:10.48550/arxiv.2503.18931
Self-citation
Metadata
- Authors
- Meng, L., Yang, J., Tian, R., Dai, X., Wu, Z., Gao, J., & Jiang, Y.-G.
- Venue
- Advances in Neural Information Processing Systems 37
- Published
- 2024
- Pages
- 23464-23487
- ISSN
- 1049-5258 (ISSN-L)
- OpenAlex
- W4415798545
- Cited by
- 12
- References
- 3
- Citations by year
- 2026: 11 · 2025: 1
- FWCI
- 2.48
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- neural information processing systems (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- visual tokens, large language models, vision-language models, image understanding, visual representation learning
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
