Papers › VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding

VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding

22 Jan 2025arXiv:2501.13106archive 2025-07-28

Boqiang Zhang, Kehan Li, Zesen Cheng, Zhiqiang Hu, Yuqian Yuan, Guanzheng Chen, Sicong Leng, Yuming Jiang, Hang Zhang, Xin Li, Peng Jin, Wenqi Zhang, Fan Wang, Lidong Bing, Deli Zhao

In this paper, we propose VideoLLaMA3, a more advanced multimodal foundation model for image and video understanding. The core design philosophy of VideoLLaMA3 is vision-centric. The meaning of "vision-centric" is two-fold: the vision-centric training paradigm and vision-centric framework design. The key insight of our vision-centric training paradigm is that high-quality image-text data is crucial for both image and video understanding. Instead of preparing massive video-text datasets, we focus on constructing large-scale and high-quality image-text datasets. VideoLLaMA3 has four training stages: 1) Vision Encoder Adaptation, which enables vision encoder to accept images of variable resolutions as input; 2) Vision-Language Alignment, which jointly tunes the vision encoder, projector, and LLM with large-scale image-text data covering multiple types (including scene images, documents, charts) as well as text-only data. 3) Multi-task Fine-tuning, which incorporates image-text SFT data for downstream tasks and video-text data to establish a foundation for video understanding. 4) Video-centric Fine-tuning, which further improves the model's capability in video understanding. As for the framework design, to better capture fine-grained details in images, the pretrained vision encoder is adapted to encode images of varying sizes into vision tokens with corresponding numbers, rather than a fixed number of tokens. For video inputs, we reduce the number of vision tokens according to their similarity so that the representation of videos will be more precise and compact. Benefit from vision-centric designs, VideoLLaMA3 achieves compelling performances in both image and video understanding benchmarks.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 14 code samples harvested from 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 14 samples from 1 repository, 8 ran (3 with no instrument failure; 5 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 8 samples that ran has no recorded date.

damo-nlp-sg/videollama3 officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 14 samples, 8 ran (5 instrument-failed) · 6 unverified 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

14 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
5ran · our draft was wrong
2ran
6unverified

Licence: 2 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from damo-nlp-sg/videollama3. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

damo-nlp-sg/videollama3 official repository 14 samples, 8 ran (5 instrument-failed) · 6 unverified
build_mlp in 74 papers inference/transformers_api/modeling_videollama3.py ran · our draft was wrong Apache-2.0 (permissive) · d62ac690ebadd7fa · report fixture: signature depth:int/0/int, hidden_size:int/0/int, output_hidden_size:int/0/int · returned Sequential · level recorded 2026-09-22
build_vision_projector in 23 papers inference/transformers_api/modeling_videollama3.py ran Apache-2.0 (permissive) · 8409d5a94c95a154 · report fixture: signature config:StandInConfig/0/?, delay_load:bool/0/bool · returned Linear · level recorded 2026-09-24
chunk_list in 7 papers videollama3/mm_utils.py ran fingerprinted Apache-2.0 (permissive) · a8b8b3e9a82ab02e · report fixture: signature input_list:list/1/int, chunk_size:int/0/int · returned list · level recorded 2026-09-25
expand2square in 78 papers videollama3/mm_utils.py ran · our draft was wrong Apache-2.0 (permissive) · 592b3c1a88f93d7c · report fixture: signature pil_img:Image/0/?, background_color:tuple/1/int · returned Image · level recorded 2026-09-22
load_image_from_base64 in 87 papers videollama3/mm_utils.py ran · honoured contract Apache-2.0 (permissive) here; the stored copy is pointer only · 0dde2e782959c0bd · report fixture: signature image:str/0/str · returned PngImageFile · level recorded 2026-09-25
load_mm_projector videollama3/model/projector.py ran · our draft was wrong Apache-2.0 (permissive) · d8e25fe3aa75d2ce · report fixture: signature model_path:str/0/str, cache_dir:NoneType/0/?, token:NoneType/0/? · returned dict · level recorded 2026-09-22
parse_snapshot_folder videollama3/model/projector.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 04129d1d261c322a · report fixture: signature repo_id:str/0/str, cache_dir:str/0/str, repo_type:str/0/str · returned str · level recorded 2026-09-22
rotate_half in 424 papers
census: 24 implementations from 96 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32
inference/transformers_api/modeling_videollama3_encoder.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · b99eea6376d1e212 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
apply_rotary_pos_emb_vision in 20 papers inference/transformers_api/modeling_videollama3_encoder.py unverified Apache-2.0 (permissive) · 48f12d3a9c4a15e8 · report
build_vision_encoder videollama3/model/encoder.py unverified Apache-2.0 (permissive) · 771a5c9570d61ca3 · report
get_mm_adapter_state_maybe_zero_3 in 44 papers videollama3/videollama3_trainer.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · 14fb23ef45b146d1 · report
get_peft_state_maybe_zero_3 in 31 papers videollama3/videollama3_trainer.py unverified Apache-2.0 (permissive) · fa1225dfac92bc0d · report
maybe_zero_3 in 74 papers videollama3/videollama3_trainer.py unverified Apache-2.0 (permissive) · 616ffbdc154ed2d8 · report
spatial_downsampling videollama3/model/videollama3_arch.py unverified Apache-2.0 (permissive) · 285dd14346d5d119 · report

Tasks

PhilosophyVideo Question AnsweringVideo Understanding

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Question Answering NExT-QA VideoLLaMA3(7B) Accuracy 84.5 #3 of 47 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

FocusSFT

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