Papers › DEEM: Diffusion Models Serve as the Eyes of Large Language Models for Image Perception

DEEM: Diffusion Models Serve as the Eyes of Large Language Models for Image Perception

24 May 2024arXiv:2405.15232archive 2025-07-28

Run Luo, Yunshui Li, Longze Chen, Wanwei He, Ting-En Lin, Ziqiang Liu, Lei Zhang, Zikai Song, Xiaobo Xia, Tongliang Liu, Min Yang, Binyuan Hui

The development of large language models (LLMs) has significantly advanced the emergence of large multimodal models (LMMs). While LMMs have achieved tremendous success by promoting the synergy between multimodal comprehension and creation, they often face challenges when confronted with out-of-distribution data, such as which can hardly distinguish orientation, quantity, color, structure, etc. This is primarily due to their reliance on image encoders trained to encode images into task-relevant features, which may lead them to disregard irrelevant details. Delving into the modeling capabilities of diffusion models for images naturally prompts the question: Can diffusion models serve as the eyes of large language models for image perception? In this paper, we propose DEEM, a simple but effective approach that utilizes the generative feedback of diffusion models to align the semantic distributions of the image encoder. This addresses the drawbacks of previous methods that solely relied on image encoders like CLIP-ViT, thereby enhancing the model's resilience against out-of-distribution samples and reducing visual hallucinations. Importantly, this is achieved without requiring additional training modules and with fewer training parameters. We extensively evaluated DEEM on both our newly constructed RobustVQA benchmark and other well-known benchmarks, POPE and MMVP, for visual hallucination and perception. In particular, DEEM improves LMM's visual perception performance to a large extent (e.g., 4% higher on RobustVQA, 6.5% higher on MMVP and 12.8 % higher on POPE ). Compared to the state-of-the-art interleaved content generation models, DEEM exhibits enhanced robustness and a superior capacity to alleviate model hallucinations while utilizing fewer trainable parameters, less pre-training data (10%), and a smaller base model size.

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 15 code samples harvested from 1 repository linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 7 ran (3 with no instrument failure; 4 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 7 samples that ran has no recorded date.

rainbowluocs/deem officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 15 samples, 7 ran (4 instrument-failed) · 8 unverified report
znlp/language-imbalance-driven-rewarding mentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Language Imbalance Driven Rewarding for Multilingual Self-improving (arXiv:2410.08964; that paper's own run record: 8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

15 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 8 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.

2ran · honoured contract
3ran · our draft was wrong
1ran; the contract check could not run
1ran
8unverified

Licence: 0 of the 15 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 rainbowluocs/deem. “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.

rainbowluocs/deem official repository 15 samples, 7 ran (4 instrument-failed) · 8 unverified
box_iou in 34 papers uni_interleaved/utils/grounding_score.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · ce749f837424dd8c · report fixture: signature boxes1:Tensor/2/float, boxes2:Tensor/2/float · returned tuple · level recorded 2026-09-22
extract_answer in 112 papers uni_interleaved/utils/vqa_score.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · c1b06375bdb265f4 · report fixture: signature response:str/0/str · returned str · level recorded 2026-09-24
grounding_eval uni_interleaved/utils/grounding_score.py ran · our draft was wrong Apache-2.0 (permissive) · 218b45d457ba5f5b · report fixture: signature results_file:str/0/str · returned dict · level recorded 2026-09-24
load_annt_data inference.py ran Apache-2.0 (permissive) · 983c68ab9faa901c · report fixture: signature transform:callable/0/?, tokenizer:callable/0/?, num_total_token:int/0/int, truncation:bool/0/bool, num_img_token:int/0/int, generation_kwargs:dict/0/?, annt_path:str/0/str · returned list · level recorded 2026-09-24
parse_box uni_interleaved/utils/grounding_score.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 13e859c753057e62 · report fixture: signature box_str:str/0/str · returned tuple · level recorded 2026-09-24
tensor_to_pil in 16 papers uni_interleaved/utils/clip_sim_score.py ran · our draft was wrong Apache-2.0 (permissive) · 1af97eee0d5e9a78 · report fixture: signature images:Tensor/4/float · returned list · level recorded 2026-09-24
update_texts inference.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic Apache-2.0 (permissive) · 6aae1c40e557fe64 · report fixture: signature inputs:dict/0/?, text_ids:Tensor/2/int, special_token_dict:dict/0/?, num_img_token:int/0/int, pad_image_tensor:Tensor/4/float, force_gen_image_next:bool/0/bool, force_replace_gen_text:bool/0/bool, tokenizer:callable/0/?, cur_iter:int/0/int · returned tuple · level recorded, date not recorded
calculate_activation_statistics in 75 papers uni_interleaved/utils/fid_score.py unverified Apache-2.0 (permissive) · 58f3cb144de3c6f9 · report
calculate_clip_sim_i2i uni_interleaved/utils/clip_sim_score.py unverified Apache-2.0 (permissive) · a2cc9c29fefca146 · report
calculate_frechet_distance in 119 papers uni_interleaved/utils/fid_score.py unverified Apache-2.0 (permissive) · 0def50a351111624 · report
clip_rerank_generated_images uni_interleaved/utils/clip_sim_score.py unverified Apache-2.0 (permissive) · b6d159b5ffc47aa4 · report
get_activations in 100 papers uni_interleaved/utils/fid_score.py unverified Apache-2.0 (permissive) · 696501a9b5a48e4b · report
imagenet_eval uni_interleaved/utils/imagenet_score.py unverified Apache-2.0 (permissive) · 716ae138c69cc76e · report
vizwiz_vqa_eval uni_interleaved/utils/vqa_score.py unverified Apache-2.0 (permissive) · 521448a8a9392444 · report
vqa_eval uni_interleaved/utils/vqa_score.py unverified Apache-2.0 (permissive) · 2de01f2d390090d6 · report

Tasks

Hallucination

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ALIGNBASEDiffusion

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