Papers › CogVLM2: Visual Language Models for Image and Video Understanding

CogVLM2: Visual Language Models for Image and Video Understanding

29 Aug 2024arXiv:2408.16500archive 2025-07-28

Wenyi Hong, Weihan Wang, Ming Ding, Wenmeng Yu, Qingsong Lv, Yan Wang, Yean Cheng, Shiyu Huang, Junhui Ji, Zhao Xue, Lei Zhao, Zhuoyi Yang, Xiaotao Gu, Xiaohan Zhang, Guanyu Feng, Da Yin, Zihan Wang, Ji Qi, Xixuan Song, Peng Zhang, Debing Liu, Bin Xu, Juanzi Li, Yuxiao Dong, Jie Tang

Beginning with VisualGLM and CogVLM, we are continuously exploring VLMs in pursuit of enhanced vision-language fusion, efficient higher-resolution architecture, and broader modalities and applications. Here we propose the CogVLM2 family, a new generation of visual language models for image and video understanding including CogVLM2, CogVLM2-Video and GLM-4V. As an image understanding model, CogVLM2 inherits the visual expert architecture with improved training recipes in both pre-training and post-training stages, supporting input resolution up to 1344 ×1344 pixels. As a video understanding model, CogVLM2-Video integrates multi-frame input with timestamps and proposes automated temporal grounding data construction. Notably, CogVLM2 family has achieved state-of-the-art results on benchmarks like MMBench, MM-Vet, TextVQA, MVBench and VCGBench. All models are open-sourced in https://github.com/THUDM/CogVLM2 and https://github.com/THUDM/GLM-4, contributing to the advancement of the field.

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="2408.16500")

Code

Syntology Ran 12 of 17 code samples harvested from 2 repositories linked to this paper; 5 have no recorded run. Of those that ran: 1 ran · honoured contract; 11 ran with no contract checked.

By repository: official repository: 17 samples from 2 repositories, 12 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

thudm/cogvlm2 officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
thudm/glm-4 officialmentioned in paperpytorchApache-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

17 samples harvested; 12 ran; 1 honoured the contract we drafted; 5 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 · honoured contract
11ran
5unverified

Licence: 0 of the 17 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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.

b2mb thudm/cogvlm2/finetune_demo/peft_lora.py official repository ran · honoured contract fingerprinted Apache-2.0 (permissive) · 32380a050ca033d4 · report
encode_image thudm/cogvlm2/basic_demo/openai_api_request.py official repository ran Apache-2.0 (permissive) · c0b1c7a482944767 · report
get_image thudm/glm-4/inference/trans_web_vision_demo.py official repository ran Apache-2.0 (permissive) · 3ff3af9bca0ae239 · report
load_video_data thudm/cogvlm2/video_demo/gradio_demo.py official repository ran Apache-2.0 (permissive) · 421ced503e309080 · report
preprocess_messages thudm/glm-4/inference/trans_web_demo.py official repository ran Apache-2.0 (permissive) · 86830d055a7a9c5d · report
process_batch thudm/glm-4/finetune/finetune.py official repository ran Apache-2.0 (permissive) · 6c594f1eecbcd9c8 · report
process_batch thudm/glm-4/finetune/finetune_vision.py official repository ran Apache-2.0 (permissive) · 57df729a586c895a · report
process_batch_eval thudm/glm-4/finetune/finetune.py official repository ran Apache-2.0 (permissive) · 2cc2c269bdedbd33 · report
process_history_and_images thudm/cogvlm2/basic_demo/openai_api_demo.py official repository ran Apache-2.0 (permissive) · 593ba9ffcbbd977e · report
process_message thudm/glm-4/finetune/finetune.py official repository ran Apache-2.0 (permissive) · 7e93b9f509accf1c · report
process_response thudm/glm-4/demo/composite_demo/src/client.py official repository ran Apache-2.0 (permissive) · 51ffd8516205ff45 · report
recur_move_to thudm/cogvlm2/basic_demo/cli_demo_batch_inference.py official repository ran Apache-2.0 (permissive) · 80585f881584d654 · report
create_chat_completion thudm/cogvlm2/basic_demo/openai_api_request.py official repository unverified Apache-2.0 (permissive) · 3a5a5045be85ded3 · report
generate_cogvlm thudm/cogvlm2/basic_demo/openai_api_demo.py official repository unverified Apache-2.0 (permissive) · 1481999518910902 · report
generate_glm4v thudm/glm-4/inference/glm4v_server.py official repository unverified Apache-2.0 (permissive) · 66a222f9124359df · report
load_tokenizer_and_model thudm/glm-4/finetune/finetune_vision.py official repository unverified Apache-2.0 (permissive) · a000febbe236a229 · report
process_batch_eval thudm/glm-4/finetune/finetune_vision.py official repository unverified Apache-2.0 (permissive) · e816697d6260afdd · report

Tasks

Video UnderstandingVisual Question Answering

3 archive task tags without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Question Answering MM-Vet GLM-4V-Plus GPT-4 score 71.1 #10 of 231 Archive leaderboard report
Visual Question Answering MM-Vet GLM-4V-9B GPT-4 score 58.0 #42 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.

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