Papers › ConvLLaVA: Hierarchical Backbones as Visual Encoder for Large Multimodal Models

ConvLLaVA: Hierarchical Backbones as Visual Encoder for Large Multimodal Models

24 May 2024arXiv:2405.15738archive 2025-07-28

Chunjiang Ge, Sijie Cheng, ZiMing Wang, Jiale Yuan, Yuan Gao, Jun Song, Shiji Song, Gao Huang, Bo Zheng

High-resolution Large Multimodal Models (LMMs) encounter the challenges of excessive visual tokens and quadratic visual complexity. Current high-resolution LMMs address the quadratic complexity while still generating excessive visual tokens. However, the redundancy in visual tokens is the key problem as it leads to more substantial compute. To mitigate this issue, we propose ConvLLaVA, which employs ConvNeXt, a hierarchical backbone, as the visual encoder of LMM to replace Vision Transformer (ViT). ConvLLaVA compresses high-resolution images into information-rich visual features, effectively preventing the generation of excessive visual tokens. To enhance the capabilities of ConvLLaVA, we propose two critical optimizations. Since the low-resolution pretrained ConvNeXt underperforms when directly applied on high resolution, we update it to bridge the gap. Moreover, since ConvNeXt's original compression ratio is inadequate for much higher resolution inputs, we train a successive stage to further compress the visual tokens, thereby reducing redundancy. These optimizations enable ConvLLaVA to support inputs of 1536x1536 resolution generating only 576 visual tokens, capable of handling images of arbitrary aspect ratios. Experimental results demonstrate that our method achieves competitive performance with state-of-the-art models on mainstream benchmarks. The ConvLLaVA model series are publicly available at https://github.com/alibaba/conv-llava.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2405.15738")

Code

Syntology Ran 7 of 10 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 2 ran · fixture could not drive it; 4 ran with no contract checked.

By repository: official repository: 10 samples from 1 repository, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

alibaba/conv-llava officialmentioned in papermentioned on GitHubpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

10 samples harvested; 7 ran; 0 honoured the contract we drafted; 3 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
2ran · fixture could not drive it
4ran
3unverified

Licence: 0 of the 10 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from alibaba/conv-llava. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

build_transform alibaba/conv-llava/llava/eval/evaluate_grounding.py official repository ran Apache-2.0 (permissive) · b19a532af1216566 · report
divide_to_patches alibaba/conv-llava/llava/mm_utils.py official repository ran Apache-2.0 (permissive) · 7e03b180fa317c9a · report
expand2square alibaba/conv-llava/llava/eval/evaluate_grounding.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 592b3c1a88f93d7c · report
reserve_square_bbox alibaba/conv-llava/llava/eval/evaluate_grounding.py official repository ran fingerprinted Apache-2.0 (permissive) · 4ace443013224f99 · report
resize_and_pad_image alibaba/conv-llava/llava/mm_utils.py official repository ran Apache-2.0 (permissive) · 468eedeba67f1b00 · report
select_best_resolution alibaba/conv-llava/llava/mm_utils.py official repository ran · fixture could not drive it Apache-2.0 (permissive) · 3999ff487573f32c · report
unpad_image alibaba/conv-llava/llava/model/llava_arch.py official repository ran · fixture could not drive it fingerprinted Apache-2.0 (permissive) · 7606525af238fb64 · report
build_vision_tower alibaba/conv-llava/llava/model/multimodal_encoder/builder.py official repository unverified Apache-2.0 (permissive) · 4562e971e895928a · report
pretty_print_semaphore alibaba/conv-llava/llava/utils.py official repository unverified Apache-2.0 (permissive) · 37899f22fb191b37 · report
violates_moderation alibaba/conv-llava/llava/utils.py official repository unverified Apache-2.0 (permissive) · f9939a84b9a65279 · report

Tasks

Visual Question Answering

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Question Answering MM-Vet ConvLLaVA GPT-4 score 45.9 #78 of 231 Archive leaderboard report
Visual Question Answering MM-Vet ConvLLaVA Params 7B #78 of 231 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBPEConvNeXtDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformerVision Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections