Papers › LLaVA-UHD v2: an MLLM Integrating High-Resolution Feature Pyramid via Hierarchical...

LLaVA-UHD v2: an MLLM Integrating High-Resolution Feature Pyramid via Hierarchical Window Transformer

18 Dec 2024arXiv:2412.13871archive 2025-07-28

YiPeng Zhang, Yifan Liu, Zonghao Guo, Yidan Zhang, Xuesong Yang, Chi Chen, Jun Song, Bo Zheng, Yuan YAO, Zhiyuan Liu, Tat-Seng Chua, Maosong Sun

In multimodal large language models (MLLMs), vision transformers (ViTs) are widely employed for visual encoding. However, their performance in solving universal MLLM tasks is not satisfactory. We attribute it to a lack of information from diverse visual levels, impeding alignment with the various semantic granularity required for language generation. To address this issue, we present LLaVA-UHD v2, an advanced MLLM centered around a Hierarchical window transformer that enables capturing diverse visual granularity by constructing and integrating a high-resolution feature pyramid. As a vision-language projector, Hiwin transformer comprises two primary modules: (i) an inverse feature pyramid, constructed by a ViT-derived feature up-sampling process utilizing high-frequency details from an image pyramid, and (ii) hierarchical window attention, focusing on a set of key sampling features within cross-scale windows to condense multi-level feature maps. Extensive experiments demonstrate that LLaVA-UHD v2 achieves superior performance over existing MLLMs on popular benchmarks. Notably, our design brings an average boost of 3.7% across 14 benchmarks compared with the baseline method, 9.3% on DocVQA for instance. We make all the data, model checkpoint, and code publicly available to facilitate future research.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="2412.13871")

Code

Syntology Ran 7 of 11 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 2 ran · fixture could not drive it; 5 ran with no contract checked.

By repository: official repository: 11 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.

thunlp/llava-uhd 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

11 samples harvested; 7 ran; 0 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

2ran · fixture could not drive it
5ran
4unverified

Licence: 0 of the 11 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 thunlp/llava-uhd. “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.

extract_answer thunlp/llava-uhd/VLMEvalKit/vlmeval/vlm/llava_qwen2_uhd_v3.py official repository ran fingerprinted Apache-2.0 (permissive) · a76fe5da7ade58fb · report
extract_choice thunlp/llava-uhd/VLMEvalKit/vlmeval/vlm/llava_qwen2_uhd_v3.py official repository ran fingerprinted Apache-2.0 (permissive) · 46ca4942d73607af · report
extract_patches thunlp/llava-uhd/llava/mm_utils.py official repository ran · fixture could not drive it Apache-2.0 (permissive) · b0a851cae92754ff · report
extract_yes_no thunlp/llava-uhd/VLMEvalKit/vlmeval/vlm/llava_qwen2_uhd_v3.py official repository ran fingerprinted Apache-2.0 (permissive) · fb3f8b5f16ed11cb · report
get_2d_sincos_pos_embed thunlp/llava-uhd/llava/model/multimodal_projector/uhd_v1_resampler.py official repository ran fingerprinted Apache-2.0 (permissive) · 77e8a3ac46f3afec · report
get_abs_pos thunlp/llava-uhd/llava/model/multimodal_projector/uhd_v1_resampler.py official repository ran Apache-2.0 (permissive) · 17e90d5853a48fa7 · report
unpad_image thunlp/llava-uhd/llava/model/llava_arch.py official repository ran · fixture could not drive it fingerprinted Apache-2.0 (permissive) · 7606525af238fb64 · report
auto_pad_images thunlp/llava-uhd/llava/mm_utils.py official repository unverified Apache-2.0 (permissive) · 3c8823948724e269 · report
get_2d_sincos_pos_embed_from_grid thunlp/llava-uhd/llava/model/multimodal_projector/uhd_v1_resampler.py official repository unverified Apache-2.0 (permissive) · 2884deadbb637c3e · report
resize_and_center_crop thunlp/llava-uhd/llava/mm_utils.py official repository unverified Apache-2.0 (permissive) · c80358dff96c25ce · report
safe_load_tokenizer thunlp/llava-uhd/llava/conversation.py official repository unverified Apache-2.0 (permissive) · b20705b0dfd77ffc · report

Tasks

AttributeText Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SET

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